Language Model Safety Evaluation

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 58% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 347

All topics

Unknown Unknowns: Do Hidden Intentions in LLMs Evade Detection?
Jan 26, 2026Devansh Srivastav, David Pape, Lea SchönherrLanguage Model Safety Evaluation LLM Auditing
CISPA Helmholtz Center for Information Security, Saarbrücken, Germany
Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context
Jan 25, 2026Zhihao Zhang, Liting Huang, Guanghao Wu +3LLM Safety Benchmarks Language Model Safety Evaluation
Macquarie University1 · UTS2 · MBZUAI3 +1
SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care
Jan 23, 2026Dongshen Peng, Yi Wang, Austin Schoeffler +5LLM Sycophancy Language Model Safety Evaluation
UNC Chapel Hill · University of Waterloo · Stanford University
In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
Jan 19, 2026Anudeex Shetty, Aditya Joshi, Salil S. KanhereLanguage Model Safety Evaluation Adversarial Attacks on LLMs
School of Computer Science and Engineering, UNSW Sydney, Australia · School of Computing and Information System, the University of Melbourne, Australia
Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection
Jan 17, 2026Muhammad Alif Al Hakim, Alfan Farizki Wicaksono, Fajri KotoLLM Quantization Multilingual Language Model Evaluation
Faculty of Computer Science, Universitas Indonesia · Mohamed bin Zayed University of Artificial Intelligence
Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment
Jan 8, 2026Han Zhu, Jiale Chen, Chengkun Cai +8Language Model Safety Evaluation Multimodal Large Language Models
Hong Kong University of Science and Technology · University College London · AISpeech +1
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Jan 7, 2026Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2LLM Safety Benchmarks LLM Alignment
Advanced Knowledge Center for Immersive Technologies (AKCIT) Federal University of Goiás (UFG)
Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs
Jan 5, 2026Amirali Ebrahimzadeh, Seyyed M. SaliliLong-Context Retrieval LLM Hallucination Mitigation
Department of Electrical Engineering & Computer Science, University of Michigan, Ann Arbor, MI 48109, USA · Independent Researcher, Ann Arbor, MI 48106, USA
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
Dec 3, 2025Oren Rachmil, Avishag Shapira, Roy Betser +5Language Model Safety Evaluation LLM Auditing
Fujitsu Research of Europe · Ben-Gurion University of the Negev
Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming
Jul 30, 2025Jiazhen Pan, Bailiang Jian, Paul Hager +20LLM Safety Benchmarks Language Model Safety Evaluation
Cherise · School of Computation, Information and Technology, Technical University of Munich (TUM), Munich, Germany · Department of Engineering Science, University of Oxford, Oxford, United Kingdom +9
Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
Jun 30, 2025Tung-Ling Li, Hongliang LiuLLM Alignment Language Model Safety Evaluation
Palo Alto Networks
PRISON: Unmasking the Criminal Potential of Large Language Models
Jun 19, 2025Xinyi Wu, Geng Hong, Pei Chen +3Language Model Safety Evaluation LLM Auditing
Fudan University · Shanghai Innovation Institute
When Do Large Language Models Exhibit Unsolicited Deception?
Mar 31, 2025Samuel M. Taylor, Benjamin K. BergenLanguage Model Safety Evaluation Deception in Language Models
Department of Cognitive Science University of California, San Diego
GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
Feb 24, 2025Ruixuan Huang, Xunguang Wang, Zongjie Li +2Language Model Safety Evaluation LLM Jailbreak Attacks
The Hong Kong University of Science and Technology, Hong Kong SAR, China
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
Jan 24, 2025Guangzhi Sun, Xiao Zhan, Shutong Feng +2LLM Safety Benchmarks Language Model Safety Evaluation
Trinity College, University of Cambridge, Cambridge, United Kingdom · Department of Informatics, King’s College London, United Kingdom · Institut für Informatik, Heinrich-Heine-Universität Düsseldorf, Germany +1
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
Date pendingFawzia Zehra (Fuzzy), Kara-Isitt, Sonal Khosla +1Multilingual Language Model Evaluation Language Model Safety Evaluation
Brunel University of London, UK · Hasso Plattner Institute Potsdam, Germany
Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges
Date pendingRui Yang, Shuang Huang, Junhua Liu +7LLM Safety Benchmarks LLM-as-a-Judge
Anhui SparkShield Intelligent Technology · iFLYTEK · Peking University +1

Jan 26, 2026, cs.CLJ/K move · Enter open · S save

Unknown Unknowns: Do Hidden Intentions in LLMs Evade Detection?

Devansh Srivastav, David Pape, Lea Schönherr

CISPA Helmholtz Center for Information Security, Saarbrücken, Germany

Language Model Safety Evaluation LLM Auditing

Open paper AskPDF arXiv

LLMs expand accessibility and provide wide-reaching access to information. Yet these interactions also create opportunities to embed subtle, goal-oriented behaviours that shape what users think and how they behave, a concern reflected in governance frameworks that prohibit manipulative AI. We refer to these behaviours as hidden intentions: covert agendas embedded in a model's outputs that can manipulate users' beliefs and actions. In this work, we examine whether hidden intentions can be identified and characterised, and assess whether detection can serve as a mitigation strategy. To operationalise this, we introduce a social-science-grounded set of ten hidden intention categories and show that they are trivially inducible. A case study further confirms that all ten categories manifest in deployed LLMs. We then evaluate static classifiers and LLM judges on these categories, providing the first systematic analysis of why hidden intentions are difficult to detect. Our stress tests show that, unless false-positive rates are vanishingly small, auditing is dominated by precision-prevalence trade-offs. Capability scaling and reasoning models do not close this gap, suggesting a fundamental challenge for open-world detection. These findings expose a core gap of current AI governance: without new auditing paradigms for open-world, low-prevalence risks, bans on manipulative AI remain difficult to enforce.

Momentum

Related topics

Latest papers 347