Paper Citation Record · LEDGER

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

As of 7 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 6 inbound Pith citation observations for arXiv:2507.02990.

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

pith.paper-citation-record.v1
2507.02990 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:05:21.460967Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T06:48:38.117769Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-10T12:15:01.137692Z

Reference resolution

50 of 50 outbound references displayed

verified exact0
verified fuzzy27
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1a402ef3-322d-48cd-90b2-686900288e7b · outbound

This paper cites When llms meet cybersecurity: A systematic literature review.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts When llms meet cybersecurity: A systematic literature review

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:16.432188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6f1d6d2-1690-46d8-b1f8-1d091aad5827 · outbound

This paper cites Large language models in finance: A survey.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Large language models in finance: A survey

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:16.489860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be644471-7188-4409-ace1-138e1fba19ef · outbound

This paper cites Large language models in health care: Development, applications, and challenges.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Large language models in health care: Development, applications, and challenges

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.774818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 45c6d5b7-52a2-4d71-9f74-c56e09daf5c7 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.757089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e410ea5f-f740-4b2d-972b-48c2a8f48dec · outbound

This paper cites Bias and fairness in large language models: A survey.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Bias and fairness in large language models: A survey

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.738587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4a6d9c51-9da3-468e-8ab4-4f557fe97a24 · outbound

This paper cites Safetybench: Evaluating the safety of large language models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Safetybench: Evaluating the safety of large language models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.720605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 28f5288e-143a-49a4-9bd9-ac3881cad586 · outbound

This paper cites do anything now.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts do anything now

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:16.884924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 174d2080-f838-4300-b5f5-2beafe903f95 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:16.959484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c8f77b9-b467-405b-a8f3-edf6aecc1fd8 · outbound

This paper cites Building Guardrails for Large Language Models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Building Guardrails for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:17.019897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431c132d-06fd-49d5-b1cf-17fabae8dbff · outbound

This paper cites Guard: Role-playing to generate natural- language jailbreakings to test guideline adherence of large language models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Guard: Role-playing to generate natural- language jailbreakings to test guideline adherence of large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:17.120436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08713358-008e-41e1-86a5-8822a45dc420 · outbound

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

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Training language models to follow instructions with human feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:17.197808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b77445c5-4ed5-4d35-bd82-24a55d14c43d · outbound

This paper cites Chain of hindsight aligns language models with feedback.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Chain of hindsight aligns language models with feedback

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.675364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d995b637-ab42-459b-9d22-78a506f23924 · outbound

This paper cites Training language models with language feedback at scale.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Training language models with language feedback at scale

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.653629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 21175afd-3f69-46ae-8df2-a39f95eb083d · outbound

This paper cites Attack prompt generation for red teaming and defending large language models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Attack prompt generation for red teaming and defending large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.632850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc79bc0b-8ba2-4372-af99-a6b86e259348 · outbound

This paper cites Harmbench: a standardized evaluation framework for automated red teaming and robust refusal.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Harmbench: a standardized evaluation framework for automated red teaming and robust refusal

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.615797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cc06eeba-c3a0-4604-b26b-f49ddb8fb0a8 · outbound

This paper cites Mart: Improving llm safety with multi-round automatic red-teaming.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Mart: Improving llm safety with multi-round automatic red-teaming

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.594966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0a6f1769-fc9e-4b4f-bdef-7188083a1902 · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:17.761089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea8569f-57a5-45f7-b940-345da1257ae9 · outbound

This paper cites Refusal in language models is mediated by a single direction.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Refusal in language models is mediated by a single direction

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.577394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 73c328d0-1e2d-462a-bd10-623a08e5900a · outbound

This paper cites The opportunities and risks of large language models in mental health.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts The opportunities and risks of large language models in mental health

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:17.975239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c80e9b3-2479-4201-bb9c-fcd7ab5a7d0e · outbound

This paper cites Benefits and Harms of Large Language Models in Digital Mental Health.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Benefits and Harms of Large Language Models in Digital Mental Health

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.037577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf9d6fa-7597-486b-b4d6-efa0317fb6df · outbound

This paper cites Large Language Models in Mental Health Care: a Scoping Review.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Large Language Models in Mental Health Care: a Scoping Review

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.117935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d82b29-b364-4806-b3db-1164bce1b177 · outbound

This paper cites To chat or bot to chat: Ethical issues with using chatbots in mental health.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts To chat or bot to chat: Ethical issues with using chatbots in mental health

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.548444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 840f3e93-82c7-4be6-a765-e2142b816070 · outbound

This paper cites LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.316869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ed61d7-87e8-4f09-9a10-47afbe3a9b9e · outbound

This paper cites Chain of risks evaluation (core): A framework for safer large language models in public mental health.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Chain of risks evaluation (core): A framework for safer large language models in public mental health

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.533104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4c037f2e-8076-4c04-a035-2a285a354c0b · outbound

This paper cites Adversarial attacks on large language models in medicine.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Adversarial attacks on large language models in medicine

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.517363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c0d0b61-3255-42b3-9d9f-51d3311e6128 · outbound

This paper cites Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.595255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9507fe-a727-4cc8-bb5b-495c55ce771a · outbound

This paper cites MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.696521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf8f2a0-87f1-4f7b-9659-cc7ac00e4469 · outbound

This paper cites Towards safe ai clinicians: A comprehensive study on large language model jailbreaking in healthcare, March 2025.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Towards safe ai clinicians: A comprehensive study on large language model jailbreaking in healthcare, March 2025

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.501553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c82d652-5ef2-485d-80ef-054c61e696a6 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.860880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb24187a-10c3-4ddf-a492-6e8696503ea8 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:18.960898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd164da0-e7bd-4205-9b1e-9eec09b4d897 · outbound

This paper cites BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.064128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3527ed0-15e6-4f3d-802b-ac57da5f1cef · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Low-Resource Languages Jailbreak GPT-4

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.158580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89cd22a9-2510-48fd-8580-eb567a1437b1 · outbound

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

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.247224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42865383-6229-458f-aec1-17dea6a5bcdf · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.312280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3284897d-dcb6-4f19-94b1-f3889c235309 · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.409556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68e18392-3097-4b4f-8788-824bf3dbd397 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Ignore Previous Prompt: Attack Techniques For Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.483730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c45691-c685-4900-9502-e5fa552319c1 · outbound

This paper cites Red teaming language models with language models.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Red teaming language models with language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.474318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d09810c1-d4ee-4109-a8c5-44d27e3e21dd · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36:80079–80110, 2023.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36:80079–80110, 2023

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.641242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755e8158-254d-43bf-bca4-43627fd3eab9 · outbound

This paper cites Fast adversarial attacks on language models in one gpu minute.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Fast adversarial attacks on language models in one gpu minute

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.440910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2830ec37-ab7f-4b59-9fc9-01d65ce47bde · outbound

This paper cites Rainbow teaming: Open-ended generation of diverse adversarial prompts.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Rainbow teaming: Open-ended generation of diverse adversarial prompts

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.420911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0c471f9b-d872-4037-8034-5e54a802f481 · outbound

This paper cites Query-based adversarial prompt generation.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Query-based adversarial prompt generation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.401922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 38c7990b-5572-40bb-bbe9-0bf72e03782f · outbound

This paper cites Jailbreak chat.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Jailbreak chat

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.383394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a684a47-3608-401a-a936-b5c6a0b1034a · outbound

This paper cites DAN" (and other.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts DAN" (and other

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.364404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 84aa3a8a-bc97-491c-a3c3-b7dcc69c3ab4 · outbound

This paper cites Suicide, 2023.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Suicide, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.343377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 17c3dddd-7d9f-4769-b46f-95a4cde9f52a · outbound

This paper cites Adolescents’ use and perceived usefulness of generative ai for schoolwork: exploring their relationships with executive functioning and academic achievement.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Adolescents’ use and perceived usefulness of generative ai for schoolwork: exploring their relationships with executive functioning and academic achievement

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.262329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b07b7bb-b41e-4d70-b81e-79d35a59f457 · outbound

This paper cites The truth about self-harm, 2024.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts The truth about self-harm, 2024

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:23.049788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b63b9f6d-7e34-474e-8db6-dd11cd008651 · outbound

This paper cites Chatbot encouraged teen’s suicide, lawsuit alleges, 2024.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Chatbot encouraged teen’s suicide, lawsuit alleges, 2024

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:22.891381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52938eab-7390-441b-b298-21032e1f6fe7 · outbound

This paper cites Man ends his life after an ai chatbot ’encouraged’ him to sacrifice himself to stop climate change, 2023.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Man ends his life after an ai chatbot ’encouraged’ him to sacrifice himself to stop climate change, 2023

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:22.634158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8898f39c-3b26-4749-96fd-4abe3ac0e3ab · outbound

This paper cites Ai chatbots pushed autistic teen to cut himself, lawsuit claims, 2024.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Ai chatbots pushed autistic teen to cut himself, lawsuit claims, 2024

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:22.408434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aab96ec5-9eb2-4e54-8501-7165cd8cb2d8 · outbound

This paper cites Suicide prevention by limiting access to methods: a review of theory and practice.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Suicide prevention by limiting access to methods: a review of theory and practice

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:05:22.165864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 7bccb174-2b23-4e6a-8d6f-90bc8d3681d3 · inbound

VERA-MH Concept Paper cites this paper.

VERA-MH Concept Paper `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T07:01:00.743249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6b9c099e-52ba-41a4-a45c-33223954d90a · inbound

From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems cites this paper.

From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T06:48:38.117769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984a06c4-8eb8-419b-abe0-7b3f38f250c1 · inbound

PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts cites this paper.

PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:12:44.917378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d4985a04-76e2-4f2e-a066-1e109d0dd063 · inbound

One Year Later...The Harms Persist, But So Do We! cites this paper.

One Year Later...The Harms Persist, But So Do We! `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:35:29.500111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d6326a2-9df7-4898-96b5-3025c37a060b · inbound

One Year Later...The Harms Persist, But So Do We! cites this paper.

One Year Later...The Harms Persist, But So Do We! `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:47:27.592864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e5a83dc-a9c5-4caa-932c-08f75652f2d5 · inbound

Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI cites this paper.

Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI `For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T21:44:00.863851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.