Work

CoopValue: Revealing LLM Value Preferences Through Multi-Agent Cooperation

Year: 2026

Type: conference-paper

Abstract: Existing evaluations of large language models primarily rely on single-agent dilemmas or static binary-choice tasks, offering limited insight into how cooperation contexts influence LLM behavior.We introduce CoopValue, a multi-agent evaluation framework that assesses LLMs' value preferences through cooperative scenarios.CoopValue includes 1,778 scenarios spanning all pairwise conflicts among the 10 Schwartz values and three cooperation types: reciprocal, coopetitive, and altruistic.We evaluate 24 LLMs across 8 model families and examine how their value preferences vary across different cooperative contexts, showing the importance of assessing LLM value preferences in interactive, context-sensitive settings to guide the selection and deployment of LLMs aligned with desired cooperative behavior.The dataset and code are publicly available at https:// github.com/zeehen4040/CoopValue.git.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1887

Authors: Zee Hen Tang, Mi-Yen Yeh

Institutions: National Taiwan University, Academia Sinica, Institute of Information Science, Academia Sinica

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

Funders: Academia Sinica, National Taiwan University, National Science and Technology Council

OpenAlex ID: W7166820734