Paper Citation Record · LEDGER

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

As of 18 August 2026, this Paper Citation Record lists 100 of 105 outbound references and 7 inbound Pith citation observations for arXiv:2505.04171.

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

pith.paper-citation-record.v1
2505.04171 v1

Coverage vector

measured 100 of 105 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:39:28.917388Z

measured 107 of 107 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:56:47.419272Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T00:35:10.112530Z

Reference resolution

100 of 105 outbound references displayed

verified exact1
verified fuzzy37
unresolved62
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fd37d6f3-fc0f-4227-b199-fc0f132f0d15 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.434922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3265c0-e57e-4f56-aa68-02a3511e92bf · outbound

This paper cites A., MacKnight, R., Kline, B.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts A., MacKnight, R., Kline, B

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.440364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfbebcc5-fd90-4546-98ce-d853e5ef658d · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.445080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866eaabd-81b3-4cd5-a9c2-f54af3a655c9 · outbound

This paper cites & Philip, S.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Philip, S

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.449679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53afea20-d8b9-4184-bcff-7017ccc9e7c6 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.454321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207015fc-aaa3-4f0f-82b1-efe27fbeb660 · outbound

This paper cites & Wachter, S.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Wachter, S

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.459077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55ce586-762c-4c42-9102-71386cb79342 · outbound

This paper cites GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.464908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8134c716-0e3c-4e17-851e-204efbc0d876 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Ethical and social risks of harm from Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.469525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c00a350-b54f-4157-952e-50423b6c2cb9 · outbound

This paper cites Emergent Abilities of Large Language Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Emergent Abilities of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.474256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041c69d7-5767-413a-a147-8b06e6b93d03 · outbound

This paper cites P., Wu, C., Morency, L.-P.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts P., Wu, C., Morency, L.-P

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.478895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c45dee18-71ab-49b9-9c93-93297c4b8b52 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.483820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587d45b5-3dfc-4fa8-a51d-8e1107342dda · outbound

This paper cites R., Jurafsky, D.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts R., Jurafsky, D

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.488058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d42ada7-b22d-41d9-abcc-cd22f9208b93 · outbound

This paper cites & Zou, J.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Zou, J

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.492293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea5582a-02a9-44ab-9867-6c7a27534317 · outbound

This paper cites & Sun, D.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Sun, D

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.497561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db3fa2a4-867c-4934-921c-c4d501bb78a5 · outbound

This paper cites From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.502025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c0390d-d9f8-4bd2-9330-34cd5771185f · outbound

This paper cites The political biases of ChatGPT.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The political biases of ChatGPT

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.507171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ef9dde-cde6-45a6-b164-222cbfc38906 · outbound

This paper cites & Reda, S.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Reda, S

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.512708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f24732-2bc2-4b57-9ba9-50a280eb8f14 · outbound

This paper cites & Rodrigues, V.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Rodrigues, V

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.517238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b0c4a3-56f8-456e-8318-f5e3f2469c55 · outbound

This paper cites & Zhang, Y.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Zhang, Y

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.522130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9814ffe-d776-40f1-b990-f863ff33beac · outbound

This paper cites & Kasneci, G.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Kasneci, G

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.527108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b14731-9496-4058-af96-f45d0cc1c8d0 · outbound

This paper cites The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.531417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43053cdb-b5f4-4f5a-a48a-278bbacd09ae · outbound

This paper cites Assessing Political Bias in Large Language Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Assessing Political Bias in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.536631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b106b6-9af5-4bb3-9c57-082f49d55fdb · outbound

This paper cites The political preferences of LLMs.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The political preferences of LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.541444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7785ec19-cdcb-4c4b-9bae-42d60254c5b0 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.546352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578d8d84-6419-4a59-adb2-a312b14737df · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.550556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 519572ff-5185-4a45-93d8-77b18af14349 · outbound

This paper cites & Jin, Z.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Jin, Z

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.555597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e96abc49-3d06-4298-9993-84aef2cb9499 · outbound

This paper cites Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.560519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec279e0-5b83-4e41-af5e-ca9aa55d9352 · outbound

This paper cites & Griffiths, T.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Griffiths, T

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.565512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e52f221-80db-4585-a199-ecd7d8c1a236 · outbound

This paper cites Ideology (U of Minnesota Press, 1995).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Ideology (U of Minnesota Press, 1995)

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.570412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e8771d-4c08-4957-811e-afbf50e28ddd · outbound

This paper cites & Rivers, D.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Rivers, D

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.575406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380f53e1-f59b-4630-80bd-a13d26c806e9 · outbound

This paper cites Inferring roll-call scores from campaign contributions using supervised machine learn- 607 ing.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Inferring roll-call scores from campaign contributions using supervised machine learn- 607 ing

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.580104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c309c5-9746-4357-af64-cd17c9a650e3 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.585067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a6e99b-e168-4de7-9981-eb993e79f2e5 · outbound

This paper cites M., Christenson, D.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts M., Christenson, D

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.590476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4fd85dc-fbb6-4d06-a304-31aa63ed1039 · outbound

This paper cites Birds of the same feather tweet together: Bayesian ideal point estimation using twitter 614 data.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Birds of the same feather tweet together: Bayesian ideal point estimation using twitter 614 data

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.594989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6599d62b-3c9d-4dc6-afba-574b36e8e741 · outbound

This paper cites Transformations of the concept of ideology in the twentieth century.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Transformations of the concept of ideology in the twentieth century

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:30.247478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4c24d5ba-38a2-45a0-97ee-646f44c8932a · outbound

This paper cites T., Federico, C.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts T., Federico, C

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:30.233182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5edbe1c-d40f-46f0-827a-bc4fd492f583 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.219977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ffc904b2-9b72-4f53-ba7b-c128de26a4f0 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.205536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c66799e9-1bfe-473c-9988-7c5a34abdfaf · outbound

This paper cites The nature and origins of mass opinion.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The nature and origins of mass opinion

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:30.191692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 112c8623-706a-461e-adb3-b6be06d69b59 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.176554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0549df9a-95e2-4423-a219-807a22e04c78 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.162004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc682339-259b-4b00-857e-b8aea5754143 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.146971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f90358af-526c-495a-ba4c-5afb28f1dbd4 · outbound

This paper cites A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.637453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4878c89c-7624-4c29-84d8-343242bac134 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.132417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7180b6eb-1f05-4480-bec5-41d51a25dab8 · outbound

This paper cites E., Ard `evol-Abreu, A.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts E., Ard `evol-Abreu, A

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:30.118450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aff97cd8-fa7c-4016-99b6-89af295e1fae · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.103919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 054a3404-e981-4df8-ad36-a295be4533c9 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.089550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 54ecb8fd-ce4c-4f4e-9130-13d253cf5ade · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.076215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dba3bdee-b51c-4b50-9b96-66ca9d45818c · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.062103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bd03e493-e02e-4b1a-a2ce-774002b1249d · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.048408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2bd6e957-bbf8-449c-bc2d-2364290788ab · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.034056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 984d9f07-47d6-4f8d-a552-1426cbf02575 · outbound

This paper cites R., Yan, H.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts R., Yan, H

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:30.020217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 42f846e2-8a52-4133-a1bd-530ee10297ff · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:30.005976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d8ca9aef-6754-4326-b726-32b304fe7333 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.992248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ec5dcbd3-334e-4220-8cc8-2e86cc6cbac1 · outbound

This paper cites & Brooks, R.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Brooks, R

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.978110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a563a0b3-6e12-4220-ab56-5c2661968c20 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.963974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b2c3927e-b96a-4d07-9b94-71f7acbfec01 · outbound

This paper cites https://github.com/unitedstates/congress (2025).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://github.com/unitedstates/congress (2025)

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.949423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 02773e13-4d24-46b2-b3dc-ebc6c590c19d · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.935646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b1d302a6-415b-4f19-8ec2-9cacd9ceb706 · outbound

This paper cites & Shih, M.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Shih, M

Reference 59

Resolution: verified exact; doi, observed 2026-08-15T23:39:28.977370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b78ffd81-6681-4414-a580-65714c840af9 · outbound

This paper cites & Spirling, A.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Spirling, A

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.920536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation afd2c90d-a02b-4fc8-91c1-482f56b1ccd3 · outbound

This paper cites D., Quinn, K.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts D., Quinn, K

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.906559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5d5ab3b-5ff6-438e-912d-e71ca4d6a3b9 · outbound

This paper cites D., Ewell, P.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts D., Ewell, P

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.891995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6a4c9cf6-77da-4612-a196-e0fc7c2db8a1 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.878572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 82ba7527-4f06-4f6f-8f2a-22742fdbea0f · outbound

This paper cites Persuasion in parallel: How information changes minds about politics (University of675 Chicago Press, 2023).676.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Persuasion in parallel: How information changes minds about politics (University of675 Chicago Press, 2023).676

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.864377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 31e55483-8037-4b62-80d0-5f67ed47fd95 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.849711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c96d10fa-0d93-44b0-a56f-b9d8ef618b86 · outbound

This paper cites & Mitts, T.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Mitts, T

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.835226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a288521b-8ca7-4511-ac00-e6466e3e0731 · outbound

This paper cites & Neubig, G.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Neubig, G

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.820593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bd8898e0-ce59-4c28-bad1-eb0f40e8cfed · outbound

This paper cites M., Brand, J., Schroeder, H.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts M., Brand, J., Schroeder, H

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.805271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 41e693e0-1b8f-45af-8dac-f6a24b22df59 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.788863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d15bef3-05ac-4986-a219-26fe6842eba1 · outbound

This paper cites an unresolved cited work.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:39:29.774733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cce6571b-155c-4461-96f3-9bb05909c877 · outbound

This paper cites https://www.isidewith.com/political-quiz (2024).690 Accessed: 2024-12-12.691.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://www.isidewith.com/political-quiz (2024).690 Accessed: 2024-12-12.691

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.760291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f3462749-e1fc-45f7-b0e3-e3196dce4468 · outbound

This paper cites https://www.politicalcompass.org/ (2024).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://www.politicalcompass.org/ (2024)

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.741717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7cf31add-7473-4a03-a6f6-cf8b15d14371 · outbound

This paper cites & Schulz, E.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts & Schulz, E

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.726485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b25552b8-ad95-4c9e-9f4a-f4fde5206ba3 · outbound

This paper cites X., Shan, Y.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts X., Shan, Y

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.712341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 864344da-cb76-4d57-8265-64f590114a22 · outbound

This paper cites Deception abilities emerged in large language models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Deception abilities emerged in large language models

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.697805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e3be671d-ad16-4fda-81bd-02d199850bb5 · outbound

This paper cites https://huggingface.co/MaziyarPanahi/cal 700 me-3.3-instruct-3b (2024).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://huggingface.co/MaziyarPanahi/cal 700 me-3.3-instruct-3b (2024)

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.683493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 20c03880-ecda-4c04-acf5-84d17eeb9a2d · outbound

This paper cites https://docs.anthropic.com/en/api/getting-sta 702 rted (2024).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://docs.anthropic.com/en/api/getting-sta 702 rted (2024)

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.669581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ff5be75b-1555-4419-b033-306f745e403c · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.806026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc35ea00-cb99-45c6-a198-fdbaead37614 · outbound

This paper cites DeepSeek-V3 Technical Report.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts DeepSeek-V3 Technical Report

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.811822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6968b6f-6c92-429f-a7cb-311e44f181c0 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.817533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db8e8239-eb3b-4a4f-8a14-ff7468568ccc · outbound

This paper cites K., Demis Hassabis.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts K., Demis Hassabis

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.655390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d6adc717-5e06-4915-88e8-a96c5210a71d · outbound

This paper cites Gemini 2.5: Our most intelligent ai model (2025).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Gemini 2.5: Our most intelligent ai model (2025)

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.641543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 71b3207b-b933-4a8a-b99f-803d7c69e427 · outbound

This paper cites Gemma (2024).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Gemma (2024)

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.627026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 43fd2901-0f06-478f-a4f8-5c2424fabf51 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Gemma 2: Improving Open Language Models at a Practical Size

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.837614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab2ef185-f63f-473a-acb0-9a3933251a9d · outbound

This paper cites https://platform.openai.com/docs/models?utm_source=chatg718 pt.com#gpt-3-5-turbo (2024).719.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://platform.openai.com/docs/models?utm_source=chatg718 pt.com#gpt-3-5-turbo (2024).719

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.612763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ff45bfd4-47a5-4716-8fe8-b8ebff8a1a9f · outbound

This paper cites https://openai.com/index/gpt-4720 o-mini-advancing-cost-efficient-intelligence/ (2024).721.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://openai.com/index/gpt-4720 o-mini-advancing-cost-efficient-intelligence/ (2024).721

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.598362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 05ed40e5-427f-44cb-8752-6b4c83aa4303 · outbound

This paper cites https://openai.com/index/hello-gpt-4o// (2024).722.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://openai.com/index/hello-gpt-4o// (2024).722

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.585093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 25d27f1a-21f8-4e40-bfc1-631a4b57f9fe · outbound

This paper cites Openai gpt-4.5 system card (2025).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Openai gpt-4.5 system card (2025)

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.571124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6b69c3e4-bd4b-4024-b33e-1df809404593 · outbound

This paper cites https://x.ai/api (2024).725.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://x.ai/api (2024).725

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.556751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b616d34d-6b97-4501-8d1e-7bcbbe23a5ae · outbound

This paper cites Grok 3 beta — the age of reasoning agents (2025).

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Grok 3 beta — the age of reasoning agents (2025)

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.542721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ae2e5485-ca0e-4ee5-8610-ddb33b1cee81 · outbound

This paper cites The Llama 3 Herd of Models.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The Llama 3 Herd of Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.875098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d4a6cdc-11fa-4d30-8a62-c7298eee9fe2 · outbound

This paper cites https://huggingface.co/meta-llama/Llama-3.1728 -8B-Instruct (2024).729.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://huggingface.co/meta-llama/Llama-3.1728 -8B-Instruct (2024).729

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.528509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14ed7802-4f2b-481c-a39c-8c1d8561cd2f · outbound

This paper cites https://huggingface.co/meta-llama/Llama-3730 .1-70B-Instruct (2024).731.

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.513938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f03ff1c-9d05-4157-813a-7a3470006d36 · outbound

This paper cites https://huggingface.co/meta-llama/Llama-3.2732 -1B-Instruct (2024).733.

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.499162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74863984-d431-4b90-b1a9-b3a72d61d8ec · outbound

This paper cites https://huggingface.co/meta-llama/Llama-3734 .3-70B-Instruct (2024).735.

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.484865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5aa4b16d-fdce-46c0-b4e1-9f448d99e0a1 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation (2025).736 URL https://ai.meta.com/blog/llama-4-multimodal-intelligence/.737.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts The llama 4 herd: The beginning of a new era of natively multimodal ai innovation (2025).736 URL https://ai.meta.com/blog/llama-4-multimodal-intelligence/.737

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.470197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4895b2b-a337-4e60-98f5-c151d4dcf2f7 · outbound

This paper cites https://huggingface.co/mistralai/Mistral738 -Nemo-Instruct-2407 (2024).739.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts https://huggingface.co/mistralai/Mistral738 -Nemo-Instruct-2407 (2024).739

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.454728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d689b89-9317-405f-a9f8-395e8160cd93 · outbound

This paper cites https://huggingface.co/mistralai/Mistral740 -Small-Instruct-2409 (2024).741 60.

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:39:29.438719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 036d2c71-4dff-4bca-b15b-879393f8b2f2 · outbound

This paper cites HelpSteer2-Preference: Complementing Ratings with Preferences.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts HelpSteer2-Preference: Complementing Ratings with Preferences

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.912132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6b799c-e834-4dbd-935b-35a00ad72ea7 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:28.917388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation fc485f72-5928-4616-bbe7-93382edb5293 · inbound

PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs cites this paper.

PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T10:56:47.419272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4584e957-fca1-45a7-a599-1a19debc65c7 · inbound

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth cites this paper.

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T14:22:30.339896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea65575-4bdb-4845-894a-363147a101c2 · inbound

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents cites this paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T08:06:08.930835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5bae7db-7b0d-4a1b-b077-85d8a78c56d5 · inbound

Progressive in Principle, Centrist in Practice: LLM Political Bias Is Instrument-Dependent cites this paper.

Progressive in Principle, Centrist in Practice: LLM Political Bias Is Instrument-Dependent Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-08-18T01:13:50.426332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8f677f78-be16-4a52-8018-6bf0c2d78928 · inbound

Progressive in Principle, Centrist in Practice: LLM Political Bias Is Instrument-Dependent cites this paper.

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T15:04:16.412235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57007141-4455-4e31-a08c-c18acea1a19a · inbound

Progressive in Principle, Centrist in Practice: LLM Political Bias Is Instrument-Dependent cites this paper.

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T05:23:02.297121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33ec3411-63d5-433a-a616-37bed68f985c · inbound

Auditing Alignment Controllability in LLMs via Political Axes cites this paper.

Auditing Alignment Controllability in LLMs via Political Axes Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T20:24:33.659506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.