2026
EMNLP
EMNLP 2026
InterviewArena: Estimating Uninformative Participants through Interactive Dialogue under Incomplete Information
Abstract
AbstractWe introduce InterviewArena, an interview-style multi-agent framework for evaluating large language models (LLMs) under incomplete information. By treating missing information as a single factor, we disentangle missing-information identification from dialogue-based reasoning. Experimental results show that while LLMs can capture relative differences between participants, predicting specific missing information remains unstable, highlighting the need to evaluate these capabilities separately.