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.
Embracing LLM feedback: the role of feed- back providers and provider information for feedback effectiveness
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 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.