GuessArena automatically builds domain-specific Guess Who card decks from raw documents and uses multi-turn yes/no questioning to score LLMs on domain knowledge and reasoning.
Title resolution pending
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
-
GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning
GuessArena automatically builds domain-specific Guess Who card decks from raw documents and uses multi-turn yes/no questioning to score LLMs on domain knowledge and reasoning.