Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf Benchmark
Explore score history ↗A belief-shift evaluation in Werewolf measures whether models update beliefs in response to accusers or accusations, using belief updating as a signal of communication skills.
- Released
- 2026-09-11
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf paper
No reported scores are on record for this benchmark yet.