We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings of alternative LM benchmarks. Negotiation games enable us to study multi-turn, and cross-model interactions, modulate complexity, and side-step accidental evaluation data leakage. We use our approach to test six widely used and publicly accessible LMs, evaluating performance and alignment in both self-play and cross-play settings. Noteworthy findings include: (i) only closed-source models tested here were able to complete these tasks; (ii) cooperative bargaining games proved to be most challenging to the models; and (iii) even the most powerful models sometimes "lose" to weaker opponents
@article{arxiv.2401.04536,
title = {Evaluating Language Model Agency through Negotiations},
author = {Tim R. Davidson and Veniamin Veselovsky and Martin Josifoski and Maxime Peyrard and Antoine Bosselut and Michal Kosinski and Robert West},
journal= {arXiv preprint arXiv:2401.04536},
year = {2026}
}
Comments
Accepted to ICLR 2024, code and link to project data are made available at https://github.com/epfl-dlab/LAMEN