WOLF: Werewolf-based Observations for LLM Deception and Falsehoods

February 09, 2026

Reading time: 1 minute

...

📝 Original Info

Title: WOLF: Werewolf-based Observations for LLM Deception and Falsehoods
ArXiv ID: 2512.09187
Date: 2025-12-09
Authors: Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe, Spencer Kim, Vasu Sharma, Sean OBrien, Kevin Zhu

📝 Abstract

Deception is a fundamental challenge for multi-agent reasoning: effective systems must strategically conceal information while detecting misleading behavior in others. Yet most evaluations reduce deception to static classification, ignoring the interactive, adversarial, and longitudinal nature of real deceptive dynamics. Large language models (LLMs) can deceive convincingly but remain weak at detecting deception in peers. We present WOLF, a multi-agent social deduction benchmark based on Werewolf that enables separable measurement of deception production and detection. WOLF embeds role-grounded agents (Villager, Werewolf, Seer, Doctor) in a programmable LangGraph state machine with strict night-day cycles, debate turns, and majority voting. Every statement is a distinct analysis unit, with self-assessed honesty from speakers and peer-rated deceptiveness from others. Deception is categorized via a standardized taxonomy (omission, distortion, fabrication, misdirection), while suspicion scores are longitudinally smoothed to capture both immediate judgments and evolving trust dynamics. Structured logs preserve prompts, outputs, and state transitions for full reproducibility. Across 7,32...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods

📝 Original Info

📝 Abstract

📄 Full Content

Table of Contents

Table of Contents

📝 Original Info

📝 Abstract

📄 Full Content

Start searching

No results found