Evaluating Language Model Agency Through Negotiations
Tim Ruben Davidson, Veniamin Veselovsky, Michal Kosinski, Robert West
Abstract
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.
BibTeX
@inproceedings{
davidson2024evaluating,
title={Evaluating Language Model Agency Through Negotiations},
author={Tim Ruben Davidson and Veniamin Veselovsky and Michal Kosinski and Robert West},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=3ZqKxMHcAg}
}