Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models

TL;DR

This paper introduces a novel, game-based framework using word guessing games to evaluate large language models' intelligence, emphasizing strategic communication, adaptability, and multi-agent interaction, offering a cost-effective alternative to traditional datasets.

Contribution

It proposes DEEP and SpyGame frameworks that assess LLMs' expression, disguising, and strategic skills through interactive, multi-agent language games, advancing evaluation methods for AI intelligence.

Findings

DEEP effectively measures LLMs' descriptive and disguising abilities.

SpyGame captures LLMs' strategic thinking and adaptability.

Framework is easy to implement across multiple languages and domains.

Abstract

The automatic evaluation of LLM-based agent intelligence is critical in developing advanced LLM-based agents. Although considerable effort has been devoted to developing human-annotated evaluation datasets, such as AlpacaEval, existing techniques are costly, time-consuming, and lack adaptability. In this paper, inspired by the popular language game ``Who is Spy'', we propose to use the word guessing game to assess the intelligence performance of LLMs. Given a word, the LLM is asked to describe the word and determine its identity (spy or not) based on its and other players' descriptions. Ideally, an advanced agent should possess the ability to accurately describe a given word using an aggressive description while concurrently maximizing confusion in the conservative description, enhancing its participation in the game. To this end, we first develop DEEP to evaluate LLMs' expression and disguising abilities. DEEP requires LLM to describe a word in aggressive and conservative modes. We then introduce SpyGame, an interactive multi-agent framework designed to assess LLMs' intelligence through participation in a competitive language-based board game. Incorporating multi-agent interaction, SpyGame requires the target LLM to possess linguistic skills and strategic thinking, providing a more comprehensive evaluation of LLMs' human-like cognitive abilities and adaptability in complex communication situations. The proposed evaluation framework is very easy to implement. We collected words from multiple sources, domains, and languages and used the proposed evaluation framework to conduct experiments. Extensive experiments demonstrate that the proposed DEEP and SpyGame effectively evaluate the capabilities of various LLMs, capturing their ability to adapt to novel situations and engage in strategic communication.