Paper Citation Record · LEDGER

Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 26 inbound Pith citation observations for arXiv:2304.05335.

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

pith.paper-citation-record.v1
2304.05335 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 26 of 26 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 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:16:32.749284Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-24T05:06:00.319233Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation e1abe29f-9e10-4aed-bcf6-5bdea8dd3358 · inbound

A Survey on Large Language Model based Autonomous Agents cites this paper.

A Survey on Large Language Model based Autonomous Agents Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T04:03:00.886787Z

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 f4f50e0e-26a8-4434-aecc-24eac081f1c3 · inbound

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts cites this paper.

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:25:21.143527Z

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 9916e48f-2597-40c9-9c16-f73ad2fb5ea2 · inbound

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks cites this paper.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T17:11:00.967657Z

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 21670ddf-1bd6-40da-aa4e-82f485a2cc74 · inbound

Jailbreaking Black Box Large Language Models in Twenty Queries cites this paper.

Jailbreaking Black Box Large Language Models in Twenty Queries Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T09:48:33.209683Z

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 adeb3ebd-f9ce-4aa6-8893-a8ff65a1bb14 · inbound

Dr. Jekyll and Mr. Hyde: Two Faces of LLMs cites this paper.

Dr. Jekyll and Mr. Hyde: Two Faces of LLMs Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-24T05:06:00.323174Z

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 e4c2cbb7-da5c-4be6-89eb-d345c32b01f1 · inbound

TrustLLM: Trustworthiness in Large Language Models cites this paper.

TrustLLM: Trustworthiness in Large Language Models Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 247

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T11:17:08.703042Z

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 e9ab008d-434c-4c36-979d-c911afe699ff · inbound

Toxic Subword Pruning for Dialogue Response Generation on Large Language Models cites this paper.

Toxic Subword Pruning for Dialogue Response Generation on Large Language Models Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-23T20:23:24.806346Z

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 1ba81533-fe8b-4fc0-9a89-c3f1e18091eb · inbound

From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents cites this paper.

From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T18:27:26.170473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c731d022-e0b5-4ab2-af41-1e260a7b6081 · inbound

Risk-Averse Finetuning of Large Language Models cites this paper.

Risk-Averse Finetuning of Large Language Models Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.066525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5ab789-0452-4ebf-9415-c096ec31aed5 · inbound

Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives cites this paper.

Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T20:52:38.193214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afd8d45-dd9e-4c55-bc1e-b3f9c6c1be48 · inbound

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language cites this paper.

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T15:26:44.761325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc594ad-b278-462e-b48c-96687bb8aec7 · inbound

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns cites this paper.

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T11:03:28.304717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2025b726-2696-4717-be04-c3c9820a338c · inbound

On Almost Surely Safe Alignment of Large Language Models at Inference-Time cites this paper.

On Almost Surely Safe Alignment of Large Language Models at Inference-Time Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T16:18:40.502533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1dad92-56d5-4453-916b-6b9c423e243d · inbound

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset cites this paper.

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T18:29:43.385459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 501d0307-42cd-4a71-8345-6560b3d86d13 · inbound

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks cites this paper.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.749284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42064e71-fdde-4ab0-9cdc-443fcb4ca95f · inbound

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs cites this paper.

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.717182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c90ee0b7-7452-408d-8e22-c3a20c34c6f7 · inbound

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents cites this paper.

AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:54:57.939379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad68433a-4a5b-4a7d-a04b-d8cb0eb51a37 · inbound

Data-Centric Safety and Ethical Measures for Data and AI Governance cites this paper.

Data-Centric Safety and Ethical Measures for Data and AI Governance Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:34:07.870925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c3f700-075d-4942-ad45-f2ab4b8434ed · inbound

The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs cites this paper.

The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 115

Resolution: unresolved; no resolver link, observed 2026-08-07T10:17:26.945695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a38afe-6aa1-4af0-86c3-74970dcba164 · inbound

Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework cites this paper.

Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:15:17.984754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c0aa087-0da7-4037-87ca-fbe1f1a602f0 · inbound

Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch cites this paper.

Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:15.547515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f66dce05-8dae-467b-b1d9-8818193bc4dc · inbound

Towards Trustworthy AI: Characterizing User-Reported Risks across LLMs "In the Wild" cites this paper.

Towards Trustworthy AI: Characterizing User-Reported Risks across LLMs "In the Wild" Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T20:03:36.085653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64c10cb-f32c-46fc-b2ef-1d39ba3bfc59 · inbound

Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment cites this paper.

Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T12:27:28.661682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f69773-5492-4d80-bf51-95910bcb15cc · inbound

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching cites this paper.

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 133

Resolution: verified exact; arxiv_id, observed 2026-05-13T04:57:17.297802Z

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 053c9985-8aee-490d-ad19-f32d181ccbe0 · inbound

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching cites this paper.

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 133

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:45:06.563797Z

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 e2cf011e-77b4-4cc3-82da-3135301afa0e · inbound

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models cites this paper.

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T01:43:27.381147Z

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.