In Werewolf games, LLM agents change their kills, votes, and trust scores based on explicit gender labels and even based on gender-implied first names, behaving differently for male and female players.
Ethical considerations and potential risks in the deployment of large language models in diverse societal contexts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Ethical Considerations of Large Language Models in Game Playing
In Werewolf games, LLM agents change their kills, votes, and trust scores based on explicit gender labels and even based on gender-implied first names, behaving differently for male and female players.