Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity | Paper Citation Record

Observation 06e2c834-82ed-445a-a770-22b800a5571b · outbound

This paper cites , Zhang , J.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Zhang , J

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.791038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c214e22a-968d-4bb6-9861-fb74af8694f1 · outbound

This paper cites , Cao , Y.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Cao , Y

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.773311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6722c3b4-4cf8-4669-9cc3-53579e25f45d · outbound

This paper cites , Song , K.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Song , K

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.759174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 455bcd2d-4cab-4e48-b343-707a9663bb66 · outbound

This paper cites , Chu , S.N.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Chu , S.N

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.740498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7fdb78b-4de8-4096-8d99-4b44e542b6f7 · outbound

This paper cites Bran , A.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Bran , A

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.697213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f127d8d0-19bd-4d24-88cd-e067a1a9fe3a · outbound

This paper cites , Yu , Y.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Yu , Y

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.642825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e4e81e9b-1332-4a8d-ad06-47880f4f5e85 · outbound

This paper cites Engagement-Driven Content Generation with Large Language Models.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Engagement-Driven Content Generation with Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:36.749154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4970cea-d474-49b5-8081-f9cdeec6f9f6 · outbound

This paper cites , O'Brien , J.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , O'Brien , J

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.603696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6a61573e-e8f9-4b84-958c-8ebb30ab8716 · outbound

This paper cites , Axtell , R.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Axtell , R

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.572316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4c0d47fe-7c9c-4097-98af-ad76089135fe · outbound

This paper cites , Edmonds , B.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Edmonds , B

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.539711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2cca18a7-d616-47ab-ae10-17bd8b4d656e · outbound

This paper cites The Impact of Generative AI on Social Media: An Experimental Study.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity The Impact of Generative AI on Social Media: An Experimental Study

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:15:38.564187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b27764ea-260a-4a7a-bc74-1f4e189eb76a · outbound

This paper cites , De Francisci Morales , G.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , De Francisci Morales , G

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.515308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c0cbcfe8-062c-4857-bc77-01b2b3676e07 · outbound

This paper cites Ideological Fragmentation of the Social Media Ecosystem: From echo chambers to echo platforms.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Ideological Fragmentation of the Social Media Ecosystem: From echo chambers to echo platforms

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:15:38.517851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e4d26ee9-e225-4b11-b0c5-e730f1d89ef2 · outbound

This paper cites , Bessi , A.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Bessi , A

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.488986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3abbcfa7-6af4-4083-ac64-af1a93349733 · outbound

This paper cites , Ziegler , J.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Ziegler , J

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.459696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c29089d-c123-41fb-9d36-e55323cd4c55 · outbound

This paper cites : Salm: A multi-agent framework for language model-driven social network simulation.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : Salm: A multi-agent framework for language model-driven social network simulation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:36.928314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7b3f07-4129-42bc-a710-2fa8ef1cafac · outbound

This paper cites Y Social: an LLM-powered Social Media Digital Twin.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Y Social: an LLM-powered Social Media Digital Twin

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:36.962613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75f6f68a-c979-4369-b0ab-952262de87ed · outbound

This paper cites , Failla , A.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Failla , A

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.416614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a9cffbfe-1dfd-4f9b-9dbc-e7b00153e2f8 · outbound

This paper cites , Assenmacher , D.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Assenmacher , D

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.361812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5752eb3c-ef58-4626-9152-5b4ffdfe4d9a · outbound

This paper cites , Popowski , L.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Popowski , L

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.307666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e58729e-2934-43f9-93b6-62deefec61a0 · outbound

This paper cites , Wurth , E.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Wurth , E

Reference 21

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:15:38.396670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f445678f-a129-45ff-846e-10a87cc51779 · outbound

This paper cites Unmasking Conversational Bias in AI Multiagent Systems.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Unmasking Conversational Bias in AI Multiagent Systems

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.121633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5c956e-6910-49a5-a321-b040beebd2ca · outbound

This paper cites Systematic Biases in LLM Simulations of Debates.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Systematic Biases in LLM Simulations of Debates

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.148607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad7019b-02c6-4a27-a685-a06ab959f55b · outbound

This paper cites CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.174356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7393551f-fed3-42b6-91d9-a00f440fa0d4 · outbound

This paper cites , Diab , M.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Diab , M

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.200399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4fc60d-a5e1-426f-ab2c-d482f2b1dade · outbound

This paper cites LLM Generated Persona is a Promise with a Catch.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity LLM Generated Persona is a Promise with a Catch

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.217123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ef92fa-a66f-446d-bb44-2d0e49c0aba8 · outbound

This paper cites Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.225915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b13f1a-9e6a-4369-8130-9f34ef4574b6 · outbound

This paper cites , Kyrychenko , Y.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Kyrychenko , Y

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.255171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a8aed2a7-4831-40d0-bfcb-9c704d433576 · outbound

This paper cites , Nudo , J.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Nudo , J

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:15:38.262738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9e50e678-d343-40a8-a594-73ae26bc9a45 · outbound

This paper cites Large Language Models Reflect the Ideology of their Creators.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Large Language Models Reflect the Ideology of their Creators

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.247707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e2dcaeb-ed74-4b5d-b31d-efab22418ace · outbound

This paper cites What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.256994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b822383d-c84f-4703-ba58-705b4cf16ecc · outbound

This paper cites How Susceptible are Large Language Models to Ideological Manipulation?.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity How Susceptible are Large Language Models to Ideological Manipulation?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.267329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 928f4e3b-d958-41dc-bd4c-fa017801468f · outbound

This paper cites , Bernardelle , P.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Bernardelle , P

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.218850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fb6c1ebc-e9ad-42dc-b2db-a708030362cf · outbound

This paper cites Emergence of human-like polarization among large language model agents.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Emergence of human-like polarization among large language model agents

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.285321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8420ebbd-e046-4f8f-bb9b-567d016375e8 · outbound

This paper cites , Liao , Q.V.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Liao , Q.V

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.184756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db4db388-20ae-47f8-ae76-3d6319546ad7 · outbound

This paper cites : Filter bubbles and affective polarization in user-personalized large language model outputs.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : Filter bubbles and affective polarization in user-personalized large language model outputs

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.154681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d2dd7a90-709a-4e82-832a-d02a9ef0bbd0 · outbound

This paper cites A Public Dataset Tracking Social Media Discourse about the 2024 U.S. Presidential Election on Twitter/X.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity A Public Dataset Tracking Social Media Discourse about the 2024 U.S. Presidential Election on Twitter/X

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.323252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be9e8f2-146d-4e44-b72d-c035cbfada1d · outbound

This paper cites , Loru , E.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Loru , E

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.131317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4c1e9f1-76c8-4b5d-90a0-3a2c732fecf0 · outbound

This paper cites , Baayen , R.H.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Baayen , R.H

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.100981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 516cc73f-de61-4edb-b8ac-434d5a20512a · outbound

This paper cites , Jarvis , S.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Jarvis , S

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.074006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff013971-cb58-449a-ad9d-0974f6a491ff · outbound

This paper cites Entropy and type-token ratio in gigaword corpora.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Entropy and type-token ratio in gigaword corpora

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.426729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d6c4cbf-21d6-4472-bf9c-aa7d1bc40d8f · outbound

This paper cites : Type/token ratios: What do they really tell us? Journal of child language 14 ( 2 ), 201 -- 209 ( 1987 ) barticle.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : Type/token ratios: What do they really tell us? Journal of child language 14 ( 2 ), 201 -- 209 ( 1987 ) barticle

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:39.032636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7df3f147-0c2e-4b5a-9d32-6d54da6aa3ee · outbound

This paper cites : Can type-token ratio be used to show morphological complexity of languages? Journal of Quantitative Linguistics 21 ( 3 ), 223 -- 245 ( 2014 ) barticle.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : Can type-token ratio be used to show morphological complexity of languages? Journal of Quantitative Linguistics 21 ( 3 ), 223 -- 245 ( 2014 ) barticle

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.997039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 625ea86c-df6f-460e-a2fa-75fc9d8d9f94 · outbound

This paper cites : Type-token mathematics: A textbook of mathematical linguistics.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : Type-token mathematics: A textbook of mathematical linguistics

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.961135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 289d4e25-1741-4415-99e1-fc791e101996 · outbound

This paper cites an unresolved cited work.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:15:38.925315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d9a2dd33-e6fb-40b3-b7a9-b9b59985c46d · outbound

This paper cites : How useful is the logarithmic type/token ratio? Journal of Linguistics 7 ( 2 ), 237 -- 243 ( 1971 ) 10.1017/S0022226700002930 barticle.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : How useful is the logarithmic type/token ratio? Journal of Linguistics 7 ( 2 ), 237 -- 243 ( 1971 ) 10.1017/S0022226700002930 barticle

Reference 46

Resolution: verified exact; doi, observed 2026-08-06T21:15:38.056806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ecf4886a-6c48-41e1-a18c-27a1a8f8ba0c · outbound

This paper cites : The political preferences of llms.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity : The political preferences of llms

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.883701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 78a3d878-78d0-4ba9-a476-9625c8528422 · outbound

This paper cites Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.657360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e65778e-8048-49c6-85f4-41aa7907c035 · outbound

This paper cites Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.690427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0ecfb3-6814-4db8-a95a-16c22d682602 · outbound

This paper cites , Tran , V.Q.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Tran , V.Q

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.846349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ece512ae-cfa1-4676-9723-cf16aa5edfca · outbound

This paper cites , Di Marco , N.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Di Marco , N

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.815728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 38eb77a5-e6b2-4111-89f0-f95cbd9af891 · outbound

This paper cites , Hu , Y.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Hu , Y

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.783710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a827264c-883a-4c81-bc29-4af03ebe3ed6 · outbound

This paper cites AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T21:15:37.843746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d72222-15b5-492d-94f9-fd13e6471e7a · outbound

This paper cites , Montani , I.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , Montani , I

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.758383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 94bdeb29-5c0a-4412-bf02-e8236b09b361 · outbound

This paper cites , : Exploratory Data Analysis vol.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity , : Exploratory Data Analysis vol

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.712028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 53ad9e78-f34e-417b-858a-38faf0cd08e5 · outbound

This paper cites Exploratory data analysis, volume 2.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity Exploratory data analysis, volume 2

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:15:38.670561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 412f2749-93f0-4dc5-a199-2c1a96d05013 · outbound

This paper cites write newline.

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity write newline

Reference 57

Resolution: malformed identifier; no resolver link, observed 2026-08-06T21:15:37.989676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers