MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments

TL;DR

This paper presents MIRAGE, a comprehensive framework for evaluating large language models' ability to perform complex social interactions through murder mystery games, revealing current models' limitations in understanding and role-playing complex human behaviors.

Contribution

Introduces MIRAGE, a novel evaluation framework with diverse scripts and metrics to assess LLMs' social interactive capabilities in complex role-playing scenarios.

Findings

GPT-4 struggles with complex social interactions in MIRAGE

MIRAGE's metrics reveal limitations in LLMs' trust and role-playing abilities

The framework provides a new benchmark for social intelligence in LLMs

Abstract

Large Language Models (LLMs) have shown remarkable capabilities in environmental perception, reasoning-based decision-making, and simulating complex human behaviors, particularly in interactive role-playing contexts. This paper introduces the Multiverse Interactive Role-play Ability General Evaluation (MIRAGE), a comprehensive framework designed to assess LLMs' proficiency in portraying advanced human behaviors through murder mystery games. MIRAGE features eight intricately crafted scripts encompassing diverse themes and styles, providing a rich simulation. To evaluate LLMs' performance, MIRAGE employs four distinct methods: the Trust Inclination Index (TII) to measure dynamics of trust and suspicion, the Clue Investigation Capability (CIC) to measure LLMs' capability of conducting information, the Interactivity Capability Index (ICI) to assess role-playing capabilities and the Script Compliance Index (SCI) to assess LLMs' capability of understanding and following instructions. Our experiments indicate that even popular models like GPT-4 face significant challenges in navigating the complexities presented by the MIRAGE. The datasets and simulation codes are available in \href{https://github.com/lime728/MIRAGE}{github}.