GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning

TL;DR

GuessArena is an adaptive, game-inspired framework for evaluating large language models' domain-specific knowledge and reasoning abilities, addressing limitations of static benchmarks by offering dynamic, interpretable, and scalable assessments.

Contribution

It introduces a novel adversarial game-based evaluation framework that dynamically assesses LLMs' domain knowledge and reasoning, improving over static benchmarks.

Findings

Effectively distinguishes LLMs in five domains

Enhances interpretability and scalability of evaluations

Demonstrates superior scenario adaptability

Abstract

The evaluation of large language models (LLMs) has traditionally relied on static benchmarks, a paradigm that poses two major limitations: (1) predefined test sets lack adaptability to diverse application domains, and (2) standardized evaluation protocols often fail to capture fine-grained assessments of domain-specific knowledge and contextual reasoning abilities. To overcome these challenges, we propose GuessArena, an adaptive evaluation framework grounded in adversarial game-based interactions. Inspired by the interactive structure of the Guess Who I Am? game, our framework seamlessly integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity. Empirical studies across five vertical domains-finance, healthcare, manufacturing, information technology, and education-demonstrate that GuessArena effectively distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness. Compared to conventional benchmarks, our method provides substantial advantages in interpretability, scalability, and scenario adaptability.