No article text was recorded for this version.
automated safety auditing
Version 1 of 162 papers71 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
- Blog: ELAB: Extensive LLM Alignment Benchmark in Persian Language
- Blog: A Framework to Assess Multilingual Vulnerabilities of LLMs
- Blog: NESSiE: The Necessary Safety Benchmark - Identifying Errors that should not Exist
- Blog: SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents
- Blog: HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Interactive AI Agents
- Blog: Safety Aware Task Planning via Large Language Models in Robotics
- Blog: S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
- Blog: LM Agents May Fail to Act on Their Own Risk Knowledge
- Blog: Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts
- Blog: Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
- Blog: Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
- Blog: A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics
- Blog: Merging Improves Self-Critique Against Jailbreak Attacks
- Blog: Medical Red Teaming Protocol of Language Models: On the Importance of User Perspectives in Healthcare Settings
- Blog: SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs
- Blog: SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
- Blog: SOSBENCH: Benchmarking Safety Alignment on Six Scientific Domains
- Blog: ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
- Blog: A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient
- Blog: SafetyBench: Evaluating the Safety of Large Language Models
- Blog: Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
- Blog: h4rm3l: A Language for Composable Jailbreak Attack Synthesis
- Blog: Introducing v0.5 of the AI Safety Benchmark from MLCommons
- Blog: SafePro: Evaluating the Safety of Professional-Level AI Agents
- Blog: S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
- Blog: Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- Blog: MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
- Blog: JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
- Blog: Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models
- Blog: JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
- Blog: A Chinese Dataset for Evaluating the Safeguards in Large Language Models
- Blog: JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
- Blog: SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
- Blog: SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
- Blog: ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
- Blog: Safety Pretraining: Toward the Next Generation of Safe AI
- Blog: Benchmarking adversarial robustness to bias elicitation in large language models: scalable automated assessment with LLM-as-a-judge
- Blog: IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
- Blog: All Languages Matter: On the Multilingual Safety of LLMs
- Blog: RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code
- Blog: Safe Multi-agent Reinforcement Learning with Natural Language Constraints
- Blog: SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
- Blog: Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
- Blog: AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic
- Blog: Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
- Blog: Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
- Blog: Flames: Benchmarking Value Alignment of LLMs in Chinese
- Blog: LLM Safety for Children
- Blog: A Benchmark for Semantic Sensitive Information in LLMs Outputs
- Blog: MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
- Blog: LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
- Blog: SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
- Blog: COVER: Context-Driven Over-Refusal Verification in LLMs
- Blog: T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
- Blog: FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models
- Blog: MARSHA: multi-agent RAG system for hazard adaptation
- Blog: SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems
- Blog: SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis
- Blog: Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression
Showing 60 of 62 papers.
History & citation
Current · Permanent link
- This direction split from Scaling AI Safety with LLM Judges (74% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_automated_safety_auditing_d60fe70e,
title = {automated safety auditing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/automated-safety-auditing/rdr_d60fe70ee1e845868f953a647c023bcb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_automated_safety_auditing_d60fe70e_v1,
title = {automated safety auditing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/automated-safety-auditing/rdr_d60fe70ee1e845868f953a647c023bcb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}