Rater State Bias in RLHF Preference Data: An Audit Framework | Paper Citation Record

Observation 084d44c5-e294-425d-915c-b488beef04f5 · outbound

This paper cites Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei.

Rater State Bias in RLHF Preference Data: An Audit Framework Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.816602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c17dd9a-bd2e-41fd-87eb-f00f3d48659c · outbound

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

Rater State Bias in RLHF Preference Data: An Audit Framework Training language models to follow instructions with human feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.819806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838797b2-39b5-4fe3-af65-0c8c3157c4f1 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.822119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05089b5a-d15f-4c47-87c2-df4a91aa4dbe · outbound

This paper cites NLPo- sitionality: Characterizing design biases of datasets and models.

Rater State Bias in RLHF Preference Data: An Audit Framework NLPo- sitionality: Characterizing design biases of datasets and models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.824952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2fcf41c-f25e-4192-b40e-8a250c190a85 · outbound

This paper cites Gordon, Michelle S.

Rater State Bias in RLHF Preference Data: An Audit Framework Gordon, Michelle S

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.827349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f04f14b4-3fa5-4eb9-b1b6-72a142774208 · outbound

This paper cites Truth is a lie: Crowd truth and the seven myths of human annotation.AI Magazine, 36(1):15–24, 2015.

Rater State Bias in RLHF Preference Data: An Audit Framework Truth is a lie: Crowd truth and the seven myths of human annotation.AI Magazine, 36(1):15–24, 2015

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.831944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3af34338-b788-4208-91ed-1e8d1ecf0d8f · outbound

This paper cites The “problem” of human label variation: On ground truth in data, modeling and evaluation.

Rater State Bias in RLHF Preference Data: An Audit Framework The “problem” of human label variation: On ground truth in data, modeling and evaluation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.834517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede7f414-bae7-4ff3-af50-907bebd9e89e · outbound

This paper cites Dealing with dis- agreements: Looking beyond the majority vote in subjective annotations.Transactions of the Association for Computational Linguistics, 10:92–110, 2022.

Rater State Bias in RLHF Preference Data: An Audit Framework Dealing with dis- agreements: Looking beyond the majority vote in subjective annotations.Transactions of the Association for Computational Linguistics, 10:92–110, 2022

Reference 8

Resolution: malformed identifier; no resolver link, observed 2026-08-02T16:22:43.836967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62355181-bc2b-4d37-a12e-3c4338c7388f · outbound

This paper cites Gray and Siddharth Suri.Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass.

Rater State Bias in RLHF Preference Data: An Audit Framework Gray and Siddharth Suri.Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.839738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73966c39-c097-414d-9490-5d97e5ca70b9 · outbound

This paper cites Roberts.Behind the Screen: Content Moderation in the Shadows of Social Media.

Rater State Bias in RLHF Preference Data: An Audit Framework Roberts.Behind the Screen: Content Moderation in the Shadows of Social Media

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.841881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca714fd2-f0c1-409a-84ec-3fdd7dd4b881 · outbound

This paper cites Incorporating worker perspectives into MTurk annotation practices for NLP.

Rater State Bias in RLHF Preference Data: An Audit Framework Incorporating worker perspectives into MTurk annotation practices for NLP

Reference 11

Resolution: verified exact; doi, observed 2026-08-02T16:24:02.909900Z

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.

Observation 16e0434f-9546-4ef5-87ca-280826a39a01 · outbound

This paper cites Analyzing dataset anno- tation quality management in the wild.Computational Linguistics, 50(3):817–866, September.

Rater State Bias in RLHF Preference Data: An Audit Framework Analyzing dataset anno- tation quality management in the wild.Computational Linguistics, 50(3):817–866, September

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.846420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a97cfa-2167-448e-95a6-de2396d1b732 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Rater State Bias in RLHF Preference Data: An Audit Framework Discovering Language Model Behaviors with Model-Written Evaluations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.850952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04bb209c-e75c-4d06-a5ca-91007072748d · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Rater State Bias in RLHF Preference Data: An Audit Framework Towards Understanding Sycophancy in Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.853514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078accd6-2358-4db9-8db6-8aaa86422955 · outbound

This paper cites Procaccia.

Rater State Bias in RLHF Preference Data: An Audit Framework Procaccia

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.856125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f172cd5-dace-4aed-9541-6d3a8c27824b · outbound

This paper cites A survey on intersectional fairness in machine learning: Notions, mitigation, and challenges.

Rater State Bias in RLHF Preference Data: An Audit Framework A survey on intersectional fairness in machine learning: Notions, mitigation, and challenges

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.858377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c5f64d-7351-4b6b-9c7d-d17dcc66250c · outbound

This paper cites Scaling laws for reward model overopti- mization.

Rater State Bias in RLHF Preference Data: An Audit Framework Scaling laws for reward model overopti- mization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.860923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c101aeed-a13c-4375-bc23-474edfb88b27 · outbound

This paper cites Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms.

Rater State Bias in RLHF Preference Data: An Audit Framework Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.863555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbb23cb-9415-4682-84ef-57d145869c67 · outbound

This paper cites Men also like shopping: Reducing gender bias amplification using corpus-level constraints.

Rater State Bias in RLHF Preference Data: An Audit Framework Men also like shopping: Reducing gender bias amplification using corpus-level constraints

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.866634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c450bc8-9232-4ac7-a061-45d7681b9cdc · outbound

This paper cites Directional bias amplification.

Rater State Bias in RLHF Preference Data: An Audit Framework Directional bias amplification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.868680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3acaeac-c525-4fc9-b1c8-b8a5b32a3757 · outbound

This paper cites A Systematic Study of Bias Amplification.

Rater State Bias in RLHF Preference Data: An Audit Framework A Systematic Study of Bias Amplification

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.870674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7af49f6-515f-4ccc-bb2a-a0271021b1e9 · outbound

This paper cites An Effective Theory of Bias Amplification.

Rater State Bias in RLHF Preference Data: An Audit Framework An Effective Theory of Bias Amplification

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.873098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc998d77-1e6c-40d0-aebb-6d64d9e6efa7 · outbound

This paper cites Pennebaker, Ryan L.

Rater State Bias in RLHF Preference Data: An Audit Framework Pennebaker, Ryan L

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.875494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba803b2-bf2d-49ab-8c4c-55a19c48fd0b · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.877484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d28a753e-9ab8-4a50-b1b4-29f3107b9943 · outbound

This paper cites Mohammad and Peter D.

Rater State Bias in RLHF Preference Data: An Audit Framework Mohammad and Peter D

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.879812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac62b7a-f5b9-4304-ba0b-b953f8eb2701 · outbound

This paper cites GoEmotions: A dataset of fine-grained emotions.

Rater State Bias in RLHF Preference Data: An Audit Framework GoEmotions: A dataset of fine-grained emotions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.882036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d645810e-e238-4cd2-8dbf-618fd1560f92 · outbound

This paper cites Towards empa- thetic open-domain conversation models: A new benchmark and dataset.

Rater State Bias in RLHF Preference Data: An Audit Framework Towards empa- thetic open-domain conversation models: A new benchmark and dataset

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.884189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eae4f2c-d52f-4b5c-b74b-ce42caaec621 · outbound

This paper cites Basic Books, 1969.

Rater State Bias in RLHF Preference Data: An Audit Framework Basic Books, 1969

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.886207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5954eb4-91f9-4d6b-b93b-14cd742ed739 · outbound

This paper cites Shaver, and Daphna Pereg.

Rater State Bias in RLHF Preference Data: An Audit Framework Shaver, and Daphna Pereg

Reference 29

Resolution: verified exact; doi, observed 2026-08-02T16:24:02.687749Z

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.

Observation 3a301433-c54e-4fb8-9c35-6a262111ec4c · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.890793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55d6efff-048b-40a1-bdf3-f149476a9b01 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.892636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c16e0f71-701a-4044-9096-e9ae3a974496 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.894564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 614d75bf-8c0c-48a2-a645-8bffe771d031 · outbound

This paper cites Truax and Robert R.

Rater State Bias in RLHF Preference Data: An Audit Framework Truax and Robert R

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.896701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0305f818-b175-4cd4-920e-e8efeb7aebd0 · outbound

This paper cites Stern.The Interpersonal World of the Infant.

Rater State Bias in RLHF Preference Data: An Audit Framework Stern.The Interpersonal World of the Infant

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.898531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd600a0b-a0c2-4a1b-8a81-991827375c16 · outbound

This paper cites Feeney and Nancy L.

Rater State Bias in RLHF Preference Data: An Audit Framework Feeney and Nancy L

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.900468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ae04b27-e69d-4d16-a4b7-8963835c34c1 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.902232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e6dc80-0923-4c83-b7cf-0f3015506024 · outbound

This paper cites Exclusive: OpenAI used kenyan workers on less than$2 per hour to make ChatGPT less toxic, January 2023.

Rater State Bias in RLHF Preference Data: An Audit Framework Exclusive: OpenAI used kenyan workers on less than$2 per hour to make ChatGPT less toxic, January 2023

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.904650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b5ea29-34c7-4473-8085-db6cc0910a2f · outbound

This paper cites Kenyan workers with AI jobs thought they had tickets to the future until the grim reality set in, November 2024.

Rater State Bias in RLHF Preference Data: An Audit Framework Kenyan workers with AI jobs thought they had tickets to the future until the grim reality set in, November 2024

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.906587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a1e518-2b40-495d-9109-a8d025d86529 · outbound

This paper cites SF tech startup Scale AI, worth$13.8b, accused of widespread wage theft, December 2024.

Rater State Bias in RLHF Preference Data: An Audit Framework SF tech startup Scale AI, worth$13.8b, accused of widespread wage theft, December 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.908326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11c5c7b-5d03-4788-adaa-6879185f201c · outbound

This paper cites What is an intracluster correlation coef- ficient? crucial concepts for primary care researchers.The Annals of Family Medicine, 2(3): 204–208, 2004.

Rater State Bias in RLHF Preference Data: An Audit Framework What is an intracluster correlation coef- ficient? crucial concepts for primary care researchers.The Annals of Family Medicine, 2(3): 204–208, 2004

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.910334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a5743c-b42c-43f1-8743-80cc040278d4 · outbound

This paper cites John Wiley & Sons, New York, 1965.

Rater State Bias in RLHF Preference Data: An Audit Framework John Wiley & Sons, New York, 1965

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.912329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 569fea05-c1c7-4857-b135-3cafd5cc7d03 · outbound

This paper cites Thompson, Douglas H.

Rater State Bias in RLHF Preference Data: An Audit Framework Thompson, Douglas H

Reference 42

Resolution: verified exact; doi, observed 2026-08-02T16:24:02.443365Z

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.

Observation 9be8f67b-cfee-4408-b03c-c889f152c5f3 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 43

Resolution: verified exact; doi, observed 2026-08-02T16:24:02.266790Z

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.

Observation 114e80ec-929d-4fed-a94a-67ab4e386bdb · outbound

This paper cites Deep Learning is Robust to Massive Label Noise.

Rater State Bias in RLHF Preference Data: An Audit Framework Deep Learning is Robust to Massive Label Noise

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.918789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdbb0533-4d06-45b9-a71c-49bbbe02b012 · outbound

This paper cites Dhillon, Pradeep K.

Rater State Bias in RLHF Preference Data: An Audit Framework Dhillon, Pradeep K

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.921124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17c0234a-babc-4955-955f-17dc5c3ba8c0 · outbound

This paper cites Learning from noisy labels with deep neural networks: A survey.IEEE Transactions on Neural Networks and Learning Systems, 34(11):8135–8153, 2023.

Rater State Bias in RLHF Preference Data: An Audit Framework Learning from noisy labels with deep neural networks: A survey.IEEE Transactions on Neural Networks and Learning Systems, 34(11):8135–8153, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.925958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48634d05-a5de-47f4-b151-7d97aea37079 · outbound

This paper cites Bharucha, Sukrit Venkatagiri, Martin J.

Rater State Bias in RLHF Preference Data: An Audit Framework Bharucha, Sukrit Venkatagiri, Martin J

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.928812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3968aab4-6931-43d4-849c-0a64d71f3c9f · outbound

This paper cites ‘it’s destroyed me completely’: Kenyan moderators decry toll of training of AI models, August 2023.

Rater State Bias in RLHF Preference Data: An Audit Framework ‘it’s destroyed me completely’: Kenyan moderators decry toll of training of AI models, August 2023

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.931017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10d13d61-9499-4106-b0c6-668458e87668 · outbound

This paper cites Kim, David K.

Rater State Bias in RLHF Preference Data: An Audit Framework Kim, David K

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.933129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6abdc2c6-cd85-4d17-bbf5-44bc97196052 · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 50

Resolution: verified exact; doi, observed 2026-08-02T16:24:02.054809Z

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.

Observation f10761a4-5f7c-4bfb-be2e-3ee7c97c3056 · outbound

This paper cites On the universality and cultural specificity of emotion recognition: A meta-analysis.Psychological Bulletin, 128(2):203–235, 2002.

Rater State Bias in RLHF Preference Data: An Audit Framework On the universality and cultural specificity of emotion recognition: A meta-analysis.Psychological Bulletin, 128(2):203–235, 2002

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.937699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15230fa5-cbcd-4983-a875-d9061c5145c1 · outbound

This paper cites Heine, and Ara Norenzayan.

Rater State Bias in RLHF Preference Data: An Audit Framework Heine, and Ara Norenzayan

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.940104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a07ba85-303a-4629-8c93-00e17026092e · outbound

This paper cites The GPT-4o shock: Emotional attachment to AI models and its impact on regulatory acceptance: A cross-cultural analysis of the immediate transition from GPT-4o to GPT-5, 2025.

Rater State Bias in RLHF Preference Data: An Audit Framework The GPT-4o shock: Emotional attachment to AI models and its impact on regulatory acceptance: A cross-cultural analysis of the immediate transition from GPT-4o to GPT-5, 2025

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.942251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0284220-2b6c-419a-abdd-99d935bda08a · outbound

This paper cites The backlash over OpenAI’s decision to retire GPT-4o shows how danger- ous AI companions can be, February 2026.

Rater State Bias in RLHF Preference Data: An Audit Framework The backlash over OpenAI’s decision to retire GPT-4o shows how danger- ous AI companions can be, February 2026

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.944311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd27ff06-3ae9-4c25-a211-9066c38ee42d · outbound

This paper cites Barsalou.

Rater State Bias in RLHF Preference Data: An Audit Framework Barsalou

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.946319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0887bbb8-331d-40bb-b304-c7a76969be59 · outbound

This paper cites Feelings-as-information theory.

Rater State Bias in RLHF Preference Data: An Audit Framework Feelings-as-information theory

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.948415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4564dc3c-3a6d-4949-9d12-f2e1694c0d0a · outbound

This paper cites When human-AI interactions become parasocial.

Rater State Bias in RLHF Preference Data: An Audit Framework When human-AI interactions become parasocial

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.950760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05c9c1a-cba9-4649-9876-235b98f50186 · outbound

This paper cites Continuum, 2005.

Rater State Bias in RLHF Preference Data: An Audit Framework Continuum, 2005

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.953334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c838e419-26ba-472c-87e3-c20d242c2968 · outbound

This paper cites Dailydialog: A manually labelled multi-turn dialogue dataset.

Rater State Bias in RLHF Preference Data: An Audit Framework Dailydialog: A manually labelled multi-turn dialogue dataset

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.955314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2791cd16-ca4a-49e8-b3a7-033d30f686f5 · outbound

This paper cites How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study.

Rater State Bias in RLHF Preference Data: An Audit Framework How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.958241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1882e12-ff35-475b-8e79-8631ca515a65 · outbound

This paper cites Investigating Affective Use and Emotional Well-being on ChatGPT.

Rater State Bias in RLHF Preference Data: An Audit Framework Investigating Affective Use and Emotional Well-being on ChatGPT

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.961967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b537275-6c1e-4f81-9ce2-38c3dd86324a · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.923727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4823dbd9-dc98-4276-bcbc-c8982578e3bd · outbound

This paper cites an unresolved cited work.

Rater State Bias in RLHF Preference Data: An Audit Framework Unresolved cited work

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T16:22:43.829641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa7504ad-88c7-413b-b7bc-d3c5fde75226 · outbound

This paper cites URL https://aclanthology.org/2024.cl-3.1/.

Rater State Bias in RLHF Preference Data: An Audit Framework URL https://aclanthology.org/2024.cl-3.1/

Reference 2024

Resolution: malformed identifier; no resolver link, observed 2026-08-02T16:22:43.848580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers