Evaluating Language Model Agency through Negotiations
This work addresses the need for better benchmarks to assess language model capabilities in real-world, interactive scenarios, though it is incremental in nature.
The paper tackled the problem of evaluating language model agency by using negotiation games, finding that only closed-source models could complete the tasks and cooperative bargaining games were most challenging.
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