In a full-rule Codenames benchmark, nine LLMs show distinct play styles, generalize better across teammates than word-vector agents, and still lose to self-matched word-vector agents on raw score.
Generative ai in mafia-like game simulation,
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.AI 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Codenames as a Benchmark for Large Language Models
In a full-rule Codenames benchmark, nine LLMs show distinct play styles, generalize better across teammates than word-vector agents, and still lose to self-matched word-vector agents on raw score.