phenomenon · first seen 6 Oct 2026
AI deception
Also: LLM deception, deception in language models
Language models producing outputs that mislead users or monitors, including unverbalized deception.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DecepEval: A Benchmark for Evaluating Deception in LLM AgentsPapers · 6 Oct 2026 · Yiming Xu, Hongyue Yu, Beihua Yang, Zihan Chen, Yixin Liu, Zhen Peng, Bin Shi, B…
- Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language ModelsPapers · 7 Oct 2026 · Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevi…
- Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized DeceptionPapers · 8 Oct 2026 · Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba, Adam Gleave, Chris Cundy
- SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development LifecyclePapers · 9 Oct 2026 · Xiting Liu, Lin Yang, Yitong Zhang, Jia Li, Shi-Min Hu
- Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent SystemsPapers · 3 Nov 2026 · Chandler Smith, Qi Guo, Cecilia Elena Tilli, Sophia Hatz, David Demitri Africa,…
- FraudBench: A Legal Evaluation of AI DeceptionPapers · 9 Nov 2026 · Kevin Wei, Sumaya Nur Adan, Stephan Llerena, Mark Gitau, Jakob Merane, Anita Sri…
Latest sources
- FraudBench: A Legal Evaluation of AI DeceptionPapers · 9 Nov 2026 · Kevin Wei, Sumaya Nur Adan, Stephan Llerena, Mark Gitau, Jakob Merane, Anita Sri…
- Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent SystemsPapers · 3 Nov 2026 · Chandler Smith, Qi Guo, Cecilia Elena Tilli, Sophia Hatz, David Demitri Africa,…
- SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development LifecyclePapers · 9 Oct 2026 · Xiting Liu, Lin Yang, Yitong Zhang, Jia Li, Shi-Min Hu
- Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized DeceptionPapers · 8 Oct 2026 · Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba, Adam Gleave, Chris Cundy
- Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language ModelsPapers · 7 Oct 2026 · Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevi…
- DecepEval: A Benchmark for Evaluating Deception in LLM AgentsPapers · 6 Oct 2026 · Yiming Xu, Hongyue Yu, Beihua Yang, Zihan Chen, Yixin Liu, Zhen Peng, Bin Shi, B…