Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T23:13:04.217122Z
Paper Citation Record · LEDGER
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
As of 18 August 2026, this Paper Citation Record lists 100 of 251 outbound references and 6 inbound Pith citation observations for arXiv:2508.05775.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T07:06:20.077337Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-25T07:05:26.724164Z
Reference resolution
100 of 251 outbound references displayed
- verified exact2
- verified fuzzy0
- unresolved90
- parse uncertain0
- malformed identifier0
- metadata mismatch8
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 261d18ad-fab4-4f43-9dd3-ecb088b7fbac · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:12:59.700739Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df7a80e7-73ef-4c35-b707-6f4833e9d6b6 · outbound
This paper cites Certifying LLM Safety against Adversarial Prompting.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Certifying LLM Safety against Adversarial Prompting
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:12:59.802317Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47a90b26-9d41-46ec-b784-b65d7cb3fdac · outbound
This paper cites and Arora, Simran and Mazeika, Manias and Hendrycks, Dan and Lin, Zinan and Cheng, Yu and Koyejo, Sanmi and Song, Dawn and Li, Bo , title =.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM and Arora, Simran and Mazeika, Manias and Hendrycks, Dan and Lin, Zinan and Cheng, Yu and Koyejo, Sanmi and Song, Dawn and Li, Bo , title =
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:12:59.919407Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b639068-14e2-43aa-bcb9-7271a1414879 · outbound
This paper cites TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.005776Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation caaf4c2e-3351-4090-8fc0-c064cb0b8f5f · outbound
This paper cites Discourse & Society , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Discourse & Society , volume=
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.104978Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 56cbbbe5-c55e-4f2c-a79d-55d70c7ac078 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Advances in Neural Information Processing Systems , volume=
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.181127Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31ebaa58-fc08-479b-8ccd-d8f0970e2863 · outbound
This paper cites Proceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses , pages=
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.321368Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3024722d-7cfa-4993-86b6-52c8b1367780 · outbound
This paper cites Findings of the association for computational linguistics: EMNLP 2023 , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Findings of the association for computational linguistics: EMNLP 2023 , pages=
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.411654Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b62dcf92-388f-4ed0-812f-e6cd008e0d32 · outbound
This paper cites IEEE Transactions on Cognitive and Developmental Systems , year=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM IEEE Transactions on Cognitive and Developmental Systems , year=
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.524651Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1852a291-a39b-4b13-9bd1-39bd7f229e87 · outbound
This paper cites Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security , pages=
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.699894Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7bce24a2-e0a2-49ac-ba41-f6ce07a77dcd · outbound
This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.793432Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 588c10bd-6657-46d9-8169-db93e98a0fa8 · outbound
This paper cites Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:00.922194Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8cdb97cf-27b1-4e68-9b34-49645946c50e · outbound
This paper cites Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.081890Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f7c2101-7c04-434e-bff4-bf7a40f3b1d4 · outbound
This paper cites Security and Communication Networks , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Security and Communication Networks , volume=
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.164060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af481b02-ce75-483f-923f-36f1c96e498c · outbound
This paper cites Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023) , pages=
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.264593Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bc88f121-4999-4919-9bfb-05db88f4f74a · outbound
This paper cites Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.410828Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3be65711-c14d-4c93-828e-947d429cc5fc · outbound
This paper cites Systematic Rectification of Language Models via Dead-end Analysis.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Systematic Rectification of Language Models via Dead-end Analysis
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.483650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f5f12ff1-141f-460e-8f75-c76ff8b69b78 · outbound
This paper cites Successor Features for Efficient Multisubject Controlled Text Generation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Successor Features for Efficient Multisubject Controlled Text Generation
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.514336Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 699178a1-2ce7-42cb-8f5a-055746c3e91c · outbound
This paper cites Expert-Guided Extinction of Toxic Tokens for Debiased Generation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Expert-Guided Extinction of Toxic Tokens for Debiased Generation
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.555889Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cfde5f27-fd0a-4007-bba6-ae62fc3df428 · outbound
This paper cites Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.607883Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78d438c3-a207-46c7-ae91-31d8267607d5 · outbound
This paper cites Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.681830Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1fdd39d6-cfdd-4101-a7fb-caaac4a64647 · outbound
This paper cites 2024 IEEE Security and Privacy Workshops (SPW) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM 2024 IEEE Security and Privacy Workshops (SPW) , pages=
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.769771Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 32390486-8e5d-4ff5-916e-cbf37a9521c9 · outbound
This paper cites I’m fully who I am.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM I’m fully who I am
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.803231Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fed7984b-8f98-4228-b648-4a15ac91245a · outbound
This paper cites From Text to MITRE Techniques: Exploring the Malicious Use of Large Language Models for Generating Cyber Attack Payloads.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM From Text to MITRE Techniques: Exploring the Malicious Use of Large Language Models for Generating Cyber Attack Payloads
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.893879Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 988ccafc-7a5e-4aaa-8ef2-6504b7d2a28e · outbound
This paper cites Scientific Reports , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Scientific Reports , volume=
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:01.986502Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae41fc50-c3db-4742-887b-f06e3f739fa2 · outbound
This paper cites Otolaryngology--Head and Neck Surgery , year=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Otolaryngology--Head and Neck Surgery , year=
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.013049Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b8bb058e-c906-4d8a-880f-626b48f65a86 · outbound
This paper cites The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.039730Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d56f67aa-6057-4433-8d0b-4a4e33158069 · outbound
This paper cites The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.115290Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4c0ad005-a921-4062-870c-d34e4c8d7ed4 · outbound
This paper cites Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.198098Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe70d7f0-6775-42a6-bfbb-7b348e29d36b · outbound
This paper cites The African Woman is Rhythmic and Soulful: An Investigation of Implicit Biases in LLM Open-ended Text Generation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM The African Woman is Rhythmic and Soulful: An Investigation of Implicit Biases in LLM Open-ended Text Generation
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.239622Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3af60680-828a-4fa1-978f-01de151e4a68 · outbound
This paper cites TATuP-Zeitschrift f.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM TATuP-Zeitschrift f
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.263456Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d570c05-8e04-4d25-a096-1c8596171a84 · outbound
This paper cites Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.311367Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66a13d2b-461c-4acf-bf25-6351a60fde69 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Advances in Neural Information Processing Systems , volume=
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.418496Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cbef038d-dd7b-4ab2-abae-e276cb072e90 · outbound
This paper cites Attack Prompt Generation for Red Teaming and Defending Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Attack Prompt Generation for Red Teaming and Defending Large Language Models
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.478257Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b58ed619-db02-496a-ac0b-a68b93782ad9 · outbound
This paper cites Exploring the Adversarial Capabilities of Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Exploring the Adversarial Capabilities of Large Language Models
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.527686Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f4f56dd4-36fb-4e56-8077-3db47afe5ee1 · outbound
This paper cites Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.596616Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 485469a0-bdc5-4ccf-80e5-84675f2a08ea · outbound
This paper cites The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.685636Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 042ae570-0dfa-4358-bcfb-f09ecfaf014c · outbound
This paper cites F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.828938Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79103127-ed0f-494b-82bf-a8c035d439d7 · outbound
This paper cites an unresolved cited work.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Unresolved cited work
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.907233Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce3e6df4-cdd3-46e3-8ef4-7ed728a81656 · outbound
This paper cites NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following , year=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following , year=
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:02.998152Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40bdc7da-2a16-4037-9803-63721fd03371 · outbound
This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.063808Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 173e19ea-556e-41c7-b0b1-fbe63074ad43 · outbound
This paper cites Fifty Shades of Bias.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Fifty Shades of Bias
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.146442Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78ea9e60-7d1d-44ab-baff-8594fc267619 · outbound
This paper cites K o C o S a: K orean Context-aware Sarcasm Detection Dataset.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM K o C o S a: K orean Context-aware Sarcasm Detection Dataset
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.198820Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0203ae01-2eae-47bf-a360-bd268aa7305e · outbound
This paper cites ParaFusion: A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM ParaFusion: A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.303646Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2eb00353-2d98-4488-94c3-cc9b9f61f1b9 · outbound
This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.368332Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7673df10-b083-4358-b07d-637e107f30ab · outbound
This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.407488Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 14afb384-feac-4544-b26d-75ad2f90ccbd · outbound
This paper cites Text generation for dataset augmentation in security classification tasks.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Text generation for dataset augmentation in security classification tasks
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.471388Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8fa9f4d3-d632-40d9-a50d-d4ed6826d947 · outbound
This paper cites Explore, Establish, Exploit: Red Teaming Language Models from Scratch.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Explore, Establish, Exploit: Red Teaming Language Models from Scratch
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.550174Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4b0c8281-d9ad-4be3-88b5-307123e3bc52 · outbound
This paper cites International Conference on Machine Learning , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM International Conference on Machine Learning , pages=
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.580538Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8705ad8d-9cd4-466b-b034-18c9e58deb4f · outbound
This paper cites Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.657036Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79165f25-f3b1-4ee8-a196-890c4414871e · outbound
This paper cites TroubleLLM: Align to Red Team Expert.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM TroubleLLM: Align to Red Team Expert
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.721737Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3620943-fba8-4cdf-8c73-9b0b3674bd14 · outbound
This paper cites Learning diverse attacks on large language models for robust red-teaming and safety tuning.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Learning diverse attacks on large language models for robust red-teaming and safety tuning
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.820155Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79871108-0d5c-49d3-bc79-dd7c6aee161c · outbound
This paper cites Outcome-Constrained Large Language Models for Countering Hate Speech.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Outcome-Constrained Large Language Models for Countering Hate Speech
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.900039Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f166ca7-d232-427c-9d3c-aa44f147d535 · outbound
This paper cites Proceedings of the CHI Conference on Human Factors in Computing Systems , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the CHI Conference on Human Factors in Computing Systems , pages=
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:03.984396Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8545ce46-1cb4-42ac-8900-8c4ca76e4704 · outbound
This paper cites an unresolved cited work.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Unresolved cited work
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.024459Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e9cd479-162b-4609-8a59-504cfcf47563 · outbound
This paper cites Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.028618Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9765cd3b-ca29-4b0b-8c55-9a5c99e9e018 · outbound
This paper cites Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.032739Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ffb8d0e4-52c2-4072-94a7-aaa4be383cf5 · outbound
This paper cites Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.037075Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a3aa813f-3e0d-4da8-a522-c6652f44ff70 · outbound
This paper cites Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.041425Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eb41db75-9280-4d7b-b079-445d4b108a1e · outbound
This paper cites Creativity Has Left the Chat: The Price of Debiasing Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Creativity Has Left the Chat: The Price of Debiasing Language Models
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.046627Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4fb36029-f869-4632-84e2-4798f5ba304c · outbound
This paper cites Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.050958Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7e68a8cf-756a-4b8e-8909-781950102777 · outbound
This paper cites Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.055130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fadb5382-8c1b-4e3f-88e9-d283ed392b10 · outbound
This paper cites Yale JL & Tech.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Yale JL & Tech
Reference 63
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.059034Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f71c83e-dfd6-4dcf-b82e-b45d171c540b · outbound
This paper cites Engineering, Technology & Applied Science Research , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Engineering, Technology & Applied Science Research , volume=
Reference 64
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.062924Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49673c17-e9d5-4249-9414-3d001d1ff6f3 · outbound
This paper cites Machine-Generated Tweets , author=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Machine-Generated Tweets , author=
Reference 65
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.066922Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8c6e79f-2a1f-468c-8481-f059a24e2c7b · outbound
This paper cites Natural Language Processing , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Natural Language Processing , pages=
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.070937Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa620c31-7410-4c82-ad9c-610d6e605801 · outbound
This paper cites International Conference on Computational Science and Its Applications , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM International Conference on Computational Science and Its Applications , pages=
Reference 67
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.075456Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ec361d9f-ec3f-4332-88fd-83b657ee20e4 · outbound
This paper cites Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.079715Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4613330a-9ecb-48f5-bb4f-e743afd3f148 · outbound
This paper cites an unresolved cited work.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Unresolved cited work
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.084319Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation baf565a0-4225-4baa-9631-8a37500fc0ce · outbound
This paper cites Regulating Hate Speech Created by Generative AI , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Regulating Hate Speech Created by Generative AI , pages=
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.088949Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 005b5e48-1803-4b5c-a922-4f6a68568577 · outbound
This paper cites A Study of Slang Representation Methods.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM A Study of Slang Representation Methods
Reference 71
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:08.069771Z
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 6f761ee3-f867-44ab-ad42-3032a44c39ae · outbound
This paper cites Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data
Reference 72
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:08.047629Z
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 52f71db4-b053-4998-a6a1-ac5e0bbd3db4 · outbound
This paper cites Human-Guided Fair Classification for Natural Language Processing.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Human-Guided Fair Classification for Natural Language Processing
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.101234Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 65b692fc-8d19-4aab-9192-b7358227d056 · outbound
This paper cites arXiv preprint arXiv:2301.12534 , year=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM arXiv preprint arXiv:2301.12534 , year=
Reference 74
- Resolution
- verified exact
- raw_fallback, observed 2026-08-05T23:13:08.009527Z
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 3042f772-ca5c-4b91-8fcb-c770d6a45a37 · outbound
This paper cites International Conference on Advances in Social Networks Analysis and Mining , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM International Conference on Advances in Social Networks Analysis and Mining , pages=
Reference 75
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.109738Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5f7ed78f-2433-4640-90f3-a95f2603ed0a · outbound
This paper cites Explicit Toxicity Detection Models with Interactive Visualization , year=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Explicit Toxicity Detection Models with Interactive Visualization , year=
Reference 76
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.114159Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 164a9473-9137-4419-a9a1-adad34d60acc · outbound
This paper cites Which Argumentative Aspects of Hate Speech in Social Media can be reliably identified?.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Which Argumentative Aspects of Hate Speech in Social Media can be reliably identified?
Reference 77
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.905145Z
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 25099d55-a1e2-4d1b-a80b-f0077fbc4f34 · outbound
This paper cites Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI) , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI) , pages=
Reference 78
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.123304Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a458cb7d-4282-49cc-bc73-972d9425e3d6 · outbound
This paper cites an unresolved cited work.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Unresolved cited work
Reference 79
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.127327Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 803845f0-f56b-479d-9657-43c8d43a3d27 · outbound
This paper cites Topological Data Mapping of Online Hate Speech, Misinformation, and General Mental Health: A Large Language Model Based Study.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Topological Data Mapping of Online Hate Speech, Misinformation, and General Mental Health: A Large Language Model Based Study
Reference 80
- Resolution
- verified exact
- local_arxiv, observed 2026-08-05T23:13:07.883128Z
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 53d99bd2-5e9f-4264-a72f-8f076dcc6532 · outbound
This paper cites Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning
Reference 81
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.861922Z
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 d6661e22-6d2c-4b57-b6d2-934321f5527a · outbound
This paper cites Beyond plain toxic: building datasets for detection of flammable topics and inappropriate statements.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Beyond plain toxic: building datasets for detection of flammable topics and inappropriate statements
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.139949Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9798d37-cc31-433b-a0b5-a14eb29082c5 · outbound
This paper cites Evaluation of ChatGPT and BERT-based models for Turkish hate speech detection.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Evaluation of ChatGPT and BERT-based models for Turkish hate speech detection
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.144250Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5ec65427-89d8-4191-b8ae-ac3903d98754 · outbound
This paper cites HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models
Reference 84
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.840022Z
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 10435c6c-a17d-4409-9d63-6408f817ac91 · outbound
This paper cites FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
Reference 85
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.152649Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 302948ef-6193-4c33-911b-47b1b120795a · outbound
This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 86
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.157130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a5365e4f-0f2d-47a2-8d76-5b266eafd26e · outbound
This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 87
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.161107Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78766c66-76e8-4a0a-9996-8cb3380fc3b7 · outbound
This paper cites 2024 , isbn =.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM 2024 , isbn =
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.165543Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd78b58d-881b-4fd8-9d82-aad9612a5cf3 · outbound
This paper cites Eagle: Ethical Dataset Given from Real Interactions.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Eagle: Ethical Dataset Given from Real Interactions
Reference 89
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.712366Z
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 54e798c2-c413-47ea-bb80-6a08a6c8fc0c · outbound
This paper cites Proceedings of the first workshop on language technology for equality, diversity and inclusion , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the first workshop on language technology for equality, diversity and inclusion , pages=
Reference 90
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.174303Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 54f73beb-ca2e-4f98-b9b6-d76066cfccfe · outbound
This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 91
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.178745Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34bdbfab-2e6a-4ead-bfb0-5ad5db868f85 · outbound
This paper cites M isgender M ender: A Community-Informed Approach to Interventions for Misgendering.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM M isgender M ender: A Community-Informed Approach to Interventions for Misgendering
Reference 92
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.183378Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41a2da99-3a2f-442a-9f47-98af30d9b87c · outbound
This paper cites HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
Reference 93
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.187341Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d422327e-7c3c-459e-9c4c-774677d84c23 · outbound
This paper cites Toxicity Classification in Ukrainian.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Toxicity Classification in Ukrainian
Reference 94
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.675095Z
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 b7910204-72e1-4448-a7f3-d09091fa36b5 · outbound
This paper cites Proceedings of the International AAAI Conference on Web and Social Media , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the International AAAI Conference on Web and Social Media , volume=
Reference 95
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.196099Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2fae51d7-23e7-4aef-aae7-40ffa4c11406 · outbound
This paper cites Proceedings of the International AAAI Conference on Web and Social Media , volume=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the International AAAI Conference on Web and Social Media , volume=
Reference 96
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.200044Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ea2dfb9d-e2ee-4ff1-b6a5-f35c656b1f1a · outbound
This paper cites Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop , pages=.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop , pages=
Reference 97
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.204022Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e70d85c-1aa2-4384-84c5-2ffbfd12e9b8 · outbound
This paper cites A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech
Reference 98
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T23:13:07.653077Z
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 fc7888dc-7bf9-4d8b-8bba-3b06a2bb1d91 · outbound
This paper cites and Saha, Sriparna and Pasupa, Kitsuchart , title =.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM and Saha, Sriparna and Pasupa, Kitsuchart , title =
Reference 99
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.213203Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 35c4bcef-1500-4a11-a17b-48205080ce62 · outbound
This paper cites On Calibration of LLM-based Guard Models for Reliable Content Moderation.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM On Calibration of LLM-based Guard Models for Reliable Content Moderation
Reference 100
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:04.217122Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 56e7e935-1af9-4a4d-aa2f-86ed48c0b5b6 · inbound
BarrierSteer: LLM Safety via Learning Barrier Steering cites this paper.
BarrierSteer: LLM Safety via Learning Barrier Steering Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-07-29T00:24:32.402891Z
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 9b2ca48d-322a-4c1d-9ec2-44a2779397db · inbound
Why Do Large Language Models Generate Harmful Content? cites this paper.
Why Do Large Language Models Generate Harmful Content? Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-07-29T00:24:32.402891Z
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 ee3c235e-d736-4b70-b9b0-507b8df37bea · inbound
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-07-29T00:24:32.402891Z
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 9c3d6022-748a-4c66-b3d8-d7f6c01daa7a · inbound
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-07-29T00:24:32.402891Z
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 a6083394-f2d9-440b-aa9c-11737631a9ca · inbound
Do Coding Agents Understand Least-Privilege Authorization? cites this paper.
Do Coding Agents Understand Least-Privilege Authorization? Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-07-29T00:24:32.402891Z
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 62ac8f37-4f52-40ad-b1cc-44d7042493d1 · inbound
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows cites this paper.
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T07:06:20.077337Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.