Pith. sign in

Paper Citation Record · LEDGER

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)

As of 8 August 2026, this Paper Citation Record lists 97 of 97 outbound references and 0 inbound Pith citation observations for arXiv:2505.21091.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.21091 v3

Coverage vector

measured 97 of 97 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:43:15.704006Z

measured 97 of 97 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

97 of 97 outbound references displayed

  • verified exact6
  • verified fuzzy2
  • unresolved83
  • parse uncertain0
  • malformed identifier3
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 24dd0f94-344c-4437-898e-86c0ac8417b8 · outbound

This paper cites GPT-4o System Card.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) GPT-4o System Card

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:05.916614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:05.916614Z digest=sha256:91b8f701cae65e919135b737f1f292fe0cfa6fcfdff0b2997d8eab499f8b2596

Observation e246fd23-812e-40e1-89c7-d8711171ad5b · outbound

This paper cites Introducing the next generation of Claude.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Introducing the next generation of Claude

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:05.998595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:05.998595Z digest=sha256:b3ec5e51fa29365932192760375801ea83ee8db26bf66540ee43941e14baac08

Observation 683f8a0d-74b7-470d-95c4-a06ce7565d2d · outbound

This paper cites Memory and new controls for ChatGPT.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Memory and new controls for ChatGPT

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.120979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.120979Z digest=sha256:88a95848119506d862eade3d995c063d12842a9d74802bc4573e8ae5aac46a05

Observation 14ec7a4a-cc54-406e-8d49-a3f302d8a653 · outbound

This paper cites Model Spec (2024/05/08).

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Model Spec (2024/05/08)

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.205160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.205160Z digest=sha256:29b74385df507839877227f907a25dc14e9947d970c7649c4659e74cb16d69ad

Observation 1e8c16f8-d5c8-47bc-891e-3066223b3915 · outbound

This paper cites Gemini API.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Gemini API

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.303011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.303011Z digest=sha256:0efc019994915bc1d74574656aa0541e91c25a10ccaf41716de900a5186a7dc0

Observation c76fda70-3910-453b-adf7-e5c90e09f66d · outbound

This paper cites Friedler, C.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Friedler, C

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.384032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.384032Z digest=sha256:1cde4f619763353ddca70937236cebc340f9b46cb7be4b879d413987766b4e69

Observation 5adb2233-a48c-47fb-b8ab-bc37740d8fd2 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.466555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.466555Z digest=sha256:3b2a8fb8bdc9269bb373281243fac400f2b22c0531468e3d0346b14b041ac080

Observation fb5dc1ae-28f7-4dfd-9fc1-8189b5762d3d · outbound

This paper cites See It from My Perspective: How Language Affects Cultural Bias in Image Understanding.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.561527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.561527Z digest=sha256:c5ce289cde8938ee7f124ba406e73d572e315c8f3fb406d4ff58a3556f623ce7

Observation a13a1ce3-0663-4d34-ae13-322b83b68dcd · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 9

Resolution
malformed identifier
no resolver link, observed 2026-08-07T13:43:06.651796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.651796Z digest=sha256:82f02fb69a28bc947d8a7c243204ba4e62c7f29d6f68afbca9daf09aa4893b19

Observation b2092979-f605-4b5c-979b-8a98ed55effb · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.700933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.700933Z digest=sha256:5549e3b01764fe9635eb6996030d309ec0dc4fe63f609f1dc57790844a0c7c1a

Observation 121e044f-7d3a-4fe8-8934-25eef7a8aed1 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.768789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.768789Z digest=sha256:ff253f725f5f782b5645f464acb972a6e1a70c431d9034e82f5551db823874fc

Observation 1d9acfbe-bc80-46a0-8bae-d64a39bebfba · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.881230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.881230Z digest=sha256:58e9a588329a5a6101a40c5066e5fde48607e1f749319158c6b36ebaa6067cb7

Observation 21a4aabc-0dfe-4578-8f1b-da2ff5cd6aa1 · outbound

This paper cites 2023.Fairness and Machine Learning: Limitations and Opportunities.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) 2023.Fairness and Machine Learning: Limitations and Opportunities

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:06.956772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:06.956772Z digest=sha256:9a81d4931aa298552e268dd647db7657324dab0514578ed650c34c2e6ee8dbc6

Observation bfe033ba-a565-40b4-bfcf-c1f9d6135108 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.038678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.038678Z digest=sha256:663ffff9a12cf5eea20a36e5f0eb1ad172e346bfd81063e4cd5c40a4370bf784

Observation f10281f9-f87e-4069-a3e8-50bc481baa87 · outbound

This paper cites The Unreasonable Effectiveness of Eccentric Automatic Prompts.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) The Unreasonable Effectiveness of Eccentric Automatic Prompts

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.106020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.106020Z digest=sha256:87d74528965cbe556d4d5b61127642654d7583cecffa73607944fc620393d064

Observation f0fa1b4b-dfe2-42c3-bb79-5439c6d6b2aa · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 17

Resolution
verified exact
doi, observed 2026-08-07T13:43:16.807697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:07.271506Z digest=sha256:2a1f42a21cc9093234826a4e71c0bb837aa49c08f9eb51c249df0baf1d47d2ab

Observation 3d3d8fb3-464f-457b-940b-a7fb3bbf086b · outbound

This paper cites Language (Technology) is Power: A Critical Survey of "Bias" in NLP.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Language (Technology) is Power: A Critical Survey of "Bias" in NLP

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.329135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.329135Z digest=sha256:66a95f91b69e892c70e98842897aa3785ba882cfb261f3bb2ce9e6973815173d

Observation 5b180507-19a5-4ea2-b05b-8f57e724824e · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) On the Opportunities and Risks of Foundation Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.390809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.390809Z digest=sha256:2d5c57e9914371d853de4551ec163d74e5c83e3dda3a99e8b951fda2be159351

Observation 39367ef3-b571-4a1d-9a45-077a114738d2 · outbound

This paper cites Language Models are Few-Shot Learners.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Language Models are Few-Shot Learners

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.459306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.459306Z digest=sha256:b12fc861179e08de9da55c9416451dae0c2ede09cdd61c8791e14e58d1fbaebb

Observation 13b25aef-b0c9-44fa-a285-a58a36495d92 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.581640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.581640Z digest=sha256:143b3563e41fa9dfff3242a4567d1f2f717c4e93fe9a97fdee5c131a3d32d70a

Observation a535ad0e-2eb5-46ec-874c-ba0b3eb368ae · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.662360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.662360Z digest=sha256:e239da352a7abd3b0f5be6651f3855b7d02fcccbcc9a54b29dfccc1ef10736f9

Observation aa6012f5-1264-4475-8a26-f7c61b7424c3 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.717922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.717922Z digest=sha256:d4f85cfdcfd1e7e056010bea20eaafbe20bfd2c68a1a6c04b1fcd1709972ced2

Observation 1d5a8e43-778d-4ed5-9cc0-754992f25195 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 26

Resolution
malformed identifier
no resolver link, observed 2026-08-07T13:43:07.799623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.799623Z digest=sha256:e00c530a15b32f04901ff6b9497c7e5f1c99fba3029d2bd3030cdd84747c9417

Observation 8b6bdb90-724f-4e3c-be93-fcb9a360cdab · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:07.861065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:07.861065Z digest=sha256:2c29abcae27da2ff24b2bb44b57b16dfc951eb69946f61e1c333a5172935d3d1

Observation e83eec37-477b-4f86-bf1d-8d28d20892c4 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.031432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.031432Z digest=sha256:9f7d87bff7be5daf6c88838145e99f6e71849e0c83f140c93ddeffaaaf334ae0

Observation 795aebe3-f904-41cd-b281-88c6e09e4b38 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.104433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.104433Z digest=sha256:2d85cfc50bf3b04c699769ae0e48e4c27ca98d8b71b6f598384ec5623b8a8d09

Observation bd2c7a15-0e9a-4eb3-90cd-09211334c2c2 · outbound

This paper cites The Llama 3 Herd of Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) The Llama 3 Herd of Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.158376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.158376Z digest=sha256:9298c5c2253eaf7ee006380bb08cade826954673b5b36ec2b54d4b913dc0c41d

Observation c08ff1fe-9b61-4b02-a9a6-6df1b9e5412e · outbound

This paper cites Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.223799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.223799Z digest=sha256:8140e6edfed10fe15fb408a64c3c8fbcf84391a788145cecbf7d4dda5a767994

Observation aec39b67-d07a-4f66-9eb7-8abbafceefa6 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.316124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.316124Z digest=sha256:6550f68be3df15169c77d0cef7ca6f3c41c17554967c906215c651da3f78a554

Observation 97038cfb-3c01-4d65-a98d-b042243d3b0a · outbound

This paper cites Equality of Opportunity in Supervised Learning.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Equality of Opportunity in Supervised Learning

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.397637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.397637Z digest=sha256:c9529de856273674f6599ecfa29fbeb27eebe06dd9161e507ba41cf7f36d74f0

Observation c5db00c2-a399-4e75-8642-c8748ba64bf4 · outbound

This paper cites On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.475859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.475859Z digest=sha256:ab0d4af2bab46f6cfd7df4f07d63041b49459de488097f13ecebd62116b360fd

Observation 48679869-ff22-4a31-8d1d-5f6d79a3e38c · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.542128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.542128Z digest=sha256:e11112aa7451480ec8e8b74be0225c58a6b8a45c8d814234e7c6bbb03963354e

Observation 2e39b234-3fd0-49c6-af80-0e8c7440012e · outbound

This paper cites Hancock, and Mor Naaman.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Hancock, and Mor Naaman

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.631306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.631306Z digest=sha256:5c9ac11977f79a6fa9138af0a53dbdc3fed36cb0bf1f4746812266a0b3573568

Observation e733ffed-9a31-4c39-a688-bdea42b24013 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.670560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.670560Z digest=sha256:d0df7f22ae0e43eab4ebcfdd83ad0b0a704026c6dd1dae1ccd196a819b663e94

Observation ed855f3e-e1af-4253-8057-34e42eafedbd · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.717027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.717027Z digest=sha256:2fb63df5bcbd4a70789a3173e9f60568af7a91c4c2b9e7338fb6ff578f20dfc6

Observation a640ff08-dce7-43c6-ba0e-9686c76d2117 · outbound

This paper cites PromptKeeper: Safeguarding System Prompts for LLMs.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) PromptKeeper: Safeguarding System Prompts for LLMs

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.837135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.837135Z digest=sha256:de95028eabb39df99e145f8467f710d34d336e3ffd3898f7b11c58d3a8a1fd0c

Observation b774e321-bb45-4fec-84da-33d7cf246ad7 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.946586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.946586Z digest=sha256:862f70c6718d691e925433a3384a06378e6f3292f9d5d0546e26a5e8676e8f8e

Observation af6e97fb-5a99-4e4a-a198-f737409c5465 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:08.995296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:08.995296Z digest=sha256:179b227cd46d43352ea6833a1d837f80d9ca4e3e11e7dcba3bdf7ae5bd19df2c

Observation ae50c3db-9471-4a03-93ee-901c123cfbb2 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.131271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.131271Z digest=sha256:8e5ac9f99a1b022e95ace7832bd47c216c39b8e698afa359694863f9f837ade2

Observation 77be6134-a96a-4b79-890a-3328579ee1d1 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.243783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.243783Z digest=sha256:69246036ae692166adaffaef0f558bb983157b9439bc2723c86ebbe5a7b6e77d

Observation 8b81b1d1-9266-4a41-a653-ad504af9fc17 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.367178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.367178Z digest=sha256:cec54e22b0c20e98d5339c3e5056b221e2b99ec04fa2f2ce97fb0116ee03a4e4

Observation 99f46e82-0400-4423-be99-9483fd978cfe · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.487579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.487579Z digest=sha256:0ba25d115de2799345ac69ea79c980e19ad1a12b70cc5643c0329e1da6c14ec8

Observation ac3e019a-cc0b-4ebf-895c-77f3c66b38d1 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.581465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.581465Z digest=sha256:1c991c72cee94fdd6ed7b69d0515b43e0112decfce03736f09a07fc1ebead5eb

Observation 47491614-70ee-4464-b3c6-d51460558f78 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.798385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.798385Z digest=sha256:7c1f954a5349793ded6bfc374290f30e0f0a1e333752b03f1522e2c1388215fd

Observation 65978c71-843b-4555-8b66-8fa8563e04a2 · outbound

This paper cites Aligning to Thousands of Preferences via System Message Generalization.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Aligning to Thousands of Preferences via System Message Generalization

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:09.863473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:09.863473Z digest=sha256:38a423ce95359bf5e6758b0f43754c217920fa5b37a79f5bc8ce153b7ebca1d7

Observation b059f607-a670-4b6b-96bc-8273ee6c60d5 · outbound

This paper cites How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies

Reference 52

Resolution
verified exact
local_arxiv, observed 2026-08-07T13:43:18.663011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:10.016446Z digest=sha256:b2278265bf755d780f6c53518b5de246dc44140c1b39f24b3b26ac33c6f6cf19

Observation 0258e95e-7e38-4518-bbf9-ee001f8c57d6 · outbound

This paper cites Artificial Intelligence as a Service.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Artificial Intelligence as a Service

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.124107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.124107Z digest=sha256:e85302b68eb8a2b42d40b8756b3dee7ada8034a1e52071c8ec8120ce93e288a8

Observation 48f50591-43fd-4578-aadb-5da0a4ae80f3 · outbound

This paper cites Measuring and Controlling Instruction (In)Stability in Language Model Dialogs.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.180049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.180049Z digest=sha256:ede86e53f14e1eb4bd13570e97a526e0600a7c5752a890e0327aa6ae6660e1d1

Observation 8efff6d8-d7b6-443d-b219-923916470a08 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.264055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.264055Z digest=sha256:43ddce4e99ae01c27bb27a0dbea5da7388ce7721672551891e2b1b47ad379165

Observation f2c1f634-5235-42b1-9cf4-cb2e3240c691 · outbound

This paper cites On Measuring Social Biases in Sentence Encoders.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) On Measuring Social Biases in Sentence Encoders

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.366759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.366759Z digest=sha256:0b894bc340a4518fe9af15133e2a312a00625aca135ab2763ab8c86fca57ba12

Observation 87962608-d00c-4c3f-b313-ab794628bdde · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.463648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.463648Z digest=sha256:04111db9e0a8650d7df28a5d021abda7b6345339bac23697fdefb3232d203c98

Observation f9db62b3-0c44-4f67-bada-f355c4f9743b · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.567052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.567052Z digest=sha256:1d61cf50806cb9a391b5e82b67f7134faeb859f20369c13b259d18136f1fa33a

Observation 57708bf5-0f28-4f7a-81cf-4af47e29c1f1 · outbound

This paper cites Can LLMs Follow Simple Rules?.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Can LLMs Follow Simple Rules?

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.747801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.747801Z digest=sha256:26296980d2672ccc1da9a17d6896b4f14dcd77b8fd601a453048a4d97a9883df

Observation 7b2e0180-f414-4087-b9cd-409d37a81010 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 60

Resolution
metadata mismatch
raw_fallback, observed 2026-08-07T13:43:18.346145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:10.880761Z digest=sha256:7e287c7a576c9e95544343e1f0b63116ae64d3f665bb7c788d7ff5fcf0fcd6b0

Observation 098ee80f-7022-48fb-b57f-bca38cf172bc · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:10.978858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:10.978858Z digest=sha256:fcd17185d1f2661970ed77374a8ac0268fa1c2a733b0cd08942e8bdc90720845

Observation aeac1f9c-5646-45b8-939f-de9aaa415973 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 62

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:43:21.112034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:11.077946Z digest=sha256:4dd430380d8a1b11b1f06e18a3f32e6aad7e1762d88cf7acb36d8d98c78113b9

Observation 267df4ab-9ea1-42f0-8cc3-ddfab0cbf849 · outbound

This paper cites Training language models to follow instructions with human feedback.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Training language models to follow instructions with human feedback

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.144625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.144625Z digest=sha256:92b943c9a21e6ad6b546474c028a9b339a97239b5f4c967ede601716a6302938

Observation 1504a275-3fcf-4fc2-927b-f6dda808f11d · outbound

This paper cites I’m fully who I am.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) I’m fully who I am

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.246269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.246269Z digest=sha256:a52bfeb029f7b9b6ab9b4f448d8120f56635142cc2f739e130b78e239f98e5ae

Observation 325fb509-7520-48bb-a736-10b457bafe2f · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 65

Resolution
verified exact
doi, observed 2026-08-07T13:43:16.548183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:11.320150Z digest=sha256:6b2c23ecbc52969e8377240eb9573e0da705a234aac0f714caa1922ee0c212ee

Observation 86088a2b-cf3e-495b-bcae-9a74cedcbe15 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 66

Resolution
verified exact
raw_fallback, observed 2026-08-07T13:43:18.138342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:11.402729Z digest=sha256:d658784c07e23c5c26880725b35cd71b9fa2558547d412fd27be93f8e7201843

Observation 0d12cdff-6bc2-4954-a1c2-c227a294ebe6 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 67

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:43:20.967591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:11.501442Z digest=sha256:d36506be2e220bdd17c84b762f885513a4e2ba7fd31db7c3019ba2e2bbcb2496

Observation 143d2225-7a76-493f-bfe9-6e9e30deb34c · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.596437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.596437Z digest=sha256:b9adc9c6d859ccdb537736c760183d1989eeaad26146a6ab2c9f9c806216617b

Observation 60be388d-0cf4-4a2e-8984-97e4ea6a4ee6 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.732043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.732043Z digest=sha256:0ea313291ba2d72fe66d49d06538db59f781b1f6414d1e974e19b119505ad3c3

Observation 8c89dd17-a705-490d-8c29-82e5e4e3fdc0 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.781481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.781481Z digest=sha256:b1948b11a40e7e19c95f702b3ac1060dcfe7f6501fe86e09cd4077398c8c418c

Observation e3e1196b-98fa-4cee-a45a-2ba7b399f925 · outbound

This paper cites A Framework for Fairness: A Systematic Review of Existing Fair AI Solutions.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) A Framework for Fairness: A Systematic Review of Existing Fair AI Solutions

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:11.948268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:11.948268Z digest=sha256:205acd438c6d6ba2027b2de4a55f7641e00e932f1a99d46109ff80c977261b5a

Observation 2d7b4109-0099-4554-b6bf-5fc1ba631cf0 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 74

Resolution
verified exact
doi, observed 2026-08-07T13:43:16.270065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:12.051369Z digest=sha256:3be68937a870d696aa68c18be2c79f723215de34b3b33929b18592357bfaa356

Observation a13fe3d4-a899-431c-adf4-e4e2ca0afd1a · outbound

This paper cites Selbst, Danah Boyd, Sorelle A.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Selbst, Danah Boyd, Sorelle A

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:12.175864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:12.175864Z digest=sha256:0503066dbbd1386f42ff22a8f6683209a8a91e6f2cc41f89d9007bd73a8e2c45

Observation 3c5341f2-f35f-4564-b2ae-f8bc675bb31a · outbound

This paper cites Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:43:20.849962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:12.250990Z digest=sha256:01ca822f9b315a68fc7f8004a3a7d6a1a5ad2300539bdd80d9d6f8061cba797e

Observation b99823cf-9468-4ef9-bc64-4c4726d7abad · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:12.444367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:12.444367Z digest=sha256:f0c11bc11b44fc7e0a28898b11324313e355511991905f563a0076a91242aaf8

Observation 28e77fae-cec1-49ac-a3f9-c2c59c77bdfc · outbound

This paper cites Large Language Model Alignment: A Survey.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Large Language Model Alignment: A Survey

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:12.553837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:12.553837Z digest=sha256:0eba11f02668babf6a78aa37cb79b576364b73223caecaac7a18b1dc7f841076

Observation ed0e976a-ea86-4781-be07-5d7cf4b800f5 · outbound

This paper cites The Woman Worked as a Babysitter: On Biases in Language Generation.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) The Woman Worked as a Babysitter: On Biases in Language Generation

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:12.720422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:12.720422Z digest=sha256:f6c4b3c79bd022c140e5392c33d00aa07308154993276b2a7886e386da0319bb

Observation 414210ad-99e8-4059-a870-3dd69e50aa47 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 80

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:43:20.645929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:12.887003Z digest=sha256:bec3570ab217e8dea6df5a302b051667d7989aab0b8f037e08d7ce8290c19dfb

Observation edc88b32-e4f8-4c86-9b0e-ebbd242af508 · outbound

This paper cites You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:13.033704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:13.033704Z digest=sha256:84069ec67bc649e9d9837d3764efc718e2ca3a81dd49a4226b6ff2ae348dba8e

Observation 93b05256-ccfd-42d6-818a-37deea78dafb · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 82

Resolution
metadata mismatch
raw_fallback, observed 2026-08-07T13:43:17.670096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:13.196877Z digest=sha256:9002aab49f3e074211b769effce20440f5da51227f901500857cf06fecaac5c0

Observation 557bb59a-ece0-4e75-a698-a0b809a94250 · outbound

This paper cites I’m sorry to hear that.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) I’m sorry to hear that

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:13.323280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:13.323280Z digest=sha256:bf23aec895b9f448baf36b410387ccb537850846536caa59f9a8073abab3933b

Observation b99248d3-87c9-440f-94d5-f6e391a5f297 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 84

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:43:20.489614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:13.543485Z digest=sha256:cf8ded013b65fabe65341d45c46b2b4d126566110d3b7d8270bca20c9cae14e7

Observation 7332f349-5656-4437-94c1-c57a7256a6a1 · outbound

This paper cites Gummadi, Adish Singla, Adrian Weller, and Muhammad Bilal Zafar.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Gummadi, Adish Singla, Adrian Weller, and Muhammad Bilal Zafar

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:13.683496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:13.683496Z digest=sha256:c7470570c71082a895c98fe749e47a70c2b193a1a874a699168787b4557a9bb7

Observation f2f8144a-d8d7-4758-a8b0-59623399d126 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:13.848402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:13.848402Z digest=sha256:7566812b91a79a60b94ac5aa957dc73acfefc45a181057b541979ca9025a2f6e

Observation ac301ce7-0a95-475a-beaf-e548e5c6bb6b · outbound

This paper cites Gray, Emma Pierson, and Karen Levy.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Gray, Emma Pierson, and Karen Levy

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.000120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.000120Z digest=sha256:c17402afd1283bb5908c2f0ce1470a8d088bf0f08ad8d6060d12bcac78aea6e0

Observation 515517b9-8942-4b84-ad56-c9c53aa68fc1 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.102036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.102036Z digest=sha256:79f3fb46179a082fc6ebc6250abafac87a9ff93ad2a7083c5bf38c3ec668ef24

Observation 2af870c2-7498-413e-8a4c-86494aefbb6f · outbound

This paper cites Evaluating and Mitigating Discrimination in Language Model Decisions.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Evaluating and Mitigating Discrimination in Language Model Decisions

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.257875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.257875Z digest=sha256:c24cf12c260faba2f25978750f8e91f5ea6ab4175dfbe2d2a98b6afbc4a83a5d

Observation 6f4851c5-6fd9-49dc-a84d-c2e1e7f955a7 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.339878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.339878Z digest=sha256:b4b89e16f2c246ece91f3aa34b038bdd87453a06d9fe5c4353bd7f9488716edb

Observation c52d7d8e-6625-403e-beac-e6bb9c9a90da · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.447179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.447179Z digest=sha256:11f445a17b9ab7024885329fd8c582c5839a5df53be491a0cd5acb0796fba8be

Observation f2c66839-14a2-4a52-bacd-ebdcea49ebbe · outbound

This paper cites DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Reference 92

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.525588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.525588Z digest=sha256:634ad51e7d3283e77cd1c6ec4e5776ea01708071c5f4f56065b48264cbf24000

Observation 28d28c42-321c-489a-9b76-4b68246e9430 · outbound

This paper cites Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers

Reference 93

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.626410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.626410Z digest=sha256:aef8d442bfc39a92ce2407495fe5a148d692aacc5e7ba442b078c07618ea5832

Observation d63ed939-21a2-474d-bf7f-d7cec26887ed · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 94

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.708432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.708432Z digest=sha256:74a82d929f8c3ef073662ec438666bf9ab04e7a1868bb7520e74327ebf0d0a02

Observation 24b600a5-aa6d-4ca1-bfad-0467072e2595 · outbound

This paper cites AI supply chain.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) AI supply chain

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:43:20.298242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:14.781924Z digest=sha256:0d12481241d50595c6c7c37c20be670c16e2b561aaec7dd055d78162d7eccb33

Observation 9844aeb5-2475-4bdf-b83d-a239852fb1d9 · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:14.862557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:14.862557Z digest=sha256:9fa0324b759b5d938c9dc00df93620be4c69ac9d7dfa4826ce3d100e30e268f3

Observation 6252e87d-98b2-4145-a58b-ef5b6b926372 · outbound

This paper cites From Parity to Preference-based Notions of Fairness in Classification.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) From Parity to Preference-based Notions of Fairness in Classification

Reference 97

Resolution
metadata mismatch
local_arxiv, observed 2026-08-07T13:43:17.173835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:14.968556Z digest=sha256:20525b147da7e58ee8a92cc78c2369e46018fdd6a831193690c8e8bd889ba9ff

Observation 72d2633f-05ab-40d6-9b39-ba8bd622f95d · outbound

This paper cites Zamfirescu-Pereira, Richmond Y.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Zamfirescu-Pereira, Richmond Y

Reference 98

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:15.074418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:15.074418Z digest=sha256:219ee86e3e8a16112889c08318b08b203301dd21198661f888b013aa118920e6

Observation c636f143-88c0-4ab2-90f8-6d86d16845ae · outbound

This paper cites Personalization of Large Language Models: A Survey.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Personalization of Large Language Models: A Survey

Reference 99

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:15.288614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:15.288614Z digest=sha256:e73148416cda711913b48c87865a5555e5c9224251220be0c6fa6493048d87bf

Observation 38d899f4-06a3-4f56-950c-ee1854b962be · outbound

This paper cites an unresolved cited work.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:43:20.101588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:15.399981Z digest=sha256:bdada7580448be6c964c686c19bf97b735d8f21c08e66420a56280a2493ead59

Observation 72b91251-3c3e-4ec6-bbdb-be5368f8a352 · outbound

This paper cites In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

Reference 101

Resolution
malformed identifier
no resolver link, observed 2026-08-07T13:43:15.149712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:15.149712Z digest=sha256:90ddf10ff5dfb0ad934ded8d4992e05cebb233b8e92fd0befce030a9336b8d4a

Observation 530448ce-aa44-4f0e-ab1f-f7fe8ec1b413 · outbound

This paper cites Yu, and Lichao Sun.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Yu, and Lichao Sun

Reference 102

Resolution
verified exact
doi, observed 2026-08-07T13:43:15.914881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T13:43:15.593608Z digest=sha256:457af6ff77ffcf1133453206c7b912af2d11f95c061744615d60cd0346f708f5

Observation 2c5a1e74-47a1-4673-a7f5-988c21fb238e · outbound

This paper cites RelayAttention for Efficient Large Language Model Serving with Long System Prompts.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) RelayAttention for Efficient Large Language Model Serving with Long System Prompts

Reference 103

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:15.704006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:15.704006Z digest=sha256:201e1bf26237d7ea7d18f96cba0f28a84193bca4e7f5f4e94382eca95f05e23d

Observation c92b4d69-993b-4400-9e7e-f7a44b6df93a · outbound

This paper cites When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models

Reference 104

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:15.476797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:15.476797Z digest=sha256:96007260a8b5cbf6588b267e621bb54948c1e6e68b6755a4d231e180711742ee

Observation db85ade9-021f-4d08-ba0c-b583862b3326 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) Towards Understanding Sycophancy in Language Models

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T13:43:12.346980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:43:12.346980Z digest=sha256:69457bd0508a323414de52c550e6f7a3f23eba239c49a2e6ba678125ec6e1bc5

Pith citing papers

No inbound Pith citation observations are available.