facebookresearch / facebookresearch/ZeroSumEval

Add support for Werewolf/Mafia 🧛

Open
#4 0 comments 0 reactions 0 assignees View on GitHub
good first issue new game
Dominant language
Python
Stars
35
Forks
3
PR merge metrics
No merged PRs in 30d

Description

Design a simplified version of Werewolf/Mafia, focusing on deception, social reasoning, and hidden roles. Ideal for assessing how well models can detect lies, make accusations, and justify their claims in a multi-agent context.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.