LLM Safety

LLM: Large Language Model

Overview

LLM safety studies how models can avoid harmful assistance, manipulation, privacy violations, and unreliable advice while still helping with legitimate requests. Approaches include safety training and data filtering, inference-time guardrails and steering, output monitoring, and mechanistic methods that probe or edit internal representations. Benchmarks increasingly test jailbreaks across languages and modalities, long conversations, tool use, and high-stakes settings such as health and cybersecurity. A central challenge is maintaining robustness against adaptive attacks and changing contexts without causing over-refusal or sacrificing utility.

Latest papers

CardsList

470 papers31 papers in the last four weeks, down 50% on the four weeks before. 0.2% of all new papers.

  1. A Neurosymbolic Approach to Natural Language Formalization and Verification

    Nov 12, 2025Chenyang An, Sam Bayless, Stefano Buliani +27Formal VerificationLLM Safety

  2. MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs

    Nov 10, 2025Liang Shan, Kaicheng Shen, Wen Wu +8LLM SafetyLLM Safety Alignment

  3. UpSafe∘^\circC: Upcycling for Controllable Safety in Large Language Models

    Oct 2, 2025Yuhao Sun, Zhuoer Xu, Shiwen Cui +4LLM SafetySafety-Utility Trade-Off in Language Models

  4. Can Large Language Models Develop Gambling Addiction?

    Sep 26, 2025Seungpil Lee, Donghyeon Shin, Yunjeong Lee +1LLM Safety

  5. Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs

    Aug 9, 2025Jinhwa Kim, Ian G. HarrisLLM Safety AlignmentLLM Safety

  6. LLMs Encode Harmfulness and Refusal Separately

    Jul 16, 2025Jiachen Zhao, Jing Huang, Zhengxuan Wu +2LLM InterpretabilityLLM Refusal Behavior

  7. Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models

    Jul 7, 2025Ziqi Miao, Lijun Li, Yuan Xiong +7Adversarial Attacks on LLMsLLM Jailbreak Attacks

  8. PRISON: Unmasking the Criminal Potential of Large Language Models

    Jun 19, 2025Xinyi Wu, Geng Hong, Pei Chen +3Language Model Safety EvaluationLLM Auditing

  9. HauntAttack: When Attack Follows Reasoning as a Shadow

    Jun 8, 2025Jingyuan Ma, Rui Li, Zheng Li +4Adversarial Attacks on LLMsJailbreak Attacks

  10. Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity

    May 23, 2025Shiyu Ni, Keping Bi, Jiafeng Guo +1LLM Uncertainty EstimationLLM Hallucination Mitigation

  11. Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models

    May 12, 2025Haoran Gu, Handing Wang, Yi Mei +2LLM Safety AlignmentLLM Safety

  12. LiteLMGuard: Seamless and Lightweight On-Device Guardrails for Small Language Models against Quantization Vulnerabilities

    May 8, 2025Kalyan Nakka, Jimmy Dani, Ausmit Mondal +1LLM GuardrailsLLM Safety

  13. Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

    Mar 8, 2025Thomas Winninger, Boussad Addad, Katarzyna KapustaAdversarial Prompt GenerationAdversarial Attacks on LLMs

  14. Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models

    Dec 21, 2024Yanxu Mao, Peipei Liu, Tiehan Cui +3Adversarial Attacks on LLMsMultimodal Large Language Models

  15. LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

    Jun 30, 2024Hye Ryung Son, Saehee Eom, Mooho Song +1Controllable Text GenerationLLM Safety

  16. Could Mobile AI be Exploited?: Understanding the Exploitations of Trust and Ethics Gap in On-Device Small Language Models

    Jun 8, 2024Kalyan Nakka, Jimmy Dani, Nitesh SaxenaLanguage Model Safety EvaluationLLM Safety

  17. LiSeCo: Linear Semantic Control for Language Generation

    May 24, 2024Emily Cheng, Carmen Amo AlonsoLanguage Model SteeringControllable Text Generation

  18. Fake News Detectors are Biased against Texts Generated by Large Language Models

    Sep 15, 2023Jinyan Su, Terry Yue Zhuo, Jonibek Mansurov +2Fake News DetectionLLM Safety