Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks

TL;DR

The paper introduces the Language Model Council, a democratic system of multiple LLMs collaboratively evaluating subjective tasks, resulting in more robust and human-aligned rankings than single-model judgments.

Contribution

It proposes a novel multi-LLM council approach for subjective evaluation, demonstrating improved robustness and alignment with human judgments over traditional single-model methods.

Findings

LMC produces more separable rankings.

LMC rankings are more consistent with human evaluations.

Using multiple LLMs enhances evaluation robustness.

Abstract

As Large Language Models (LLMs) continue to evolve, evaluating them remains a persistent challenge. Many recent evaluations use LLMs as judges to score outputs from other LLMs, often relying on a single large model like GPT-4o. However, using a single LLM judge is prone to intra-model bias, and many tasks - such as those related to emotional intelligence, creative writing, and persuasiveness - may be too subjective for a single model to judge fairly. We introduce the Language Model Council (LMC), where a group of LLMs collaborate to create tests, respond to them, and evaluate each other's responses to produce a ranking in a democratic fashion. Unlike previous approaches that focus on reducing cost or bias by using a panel of smaller models, our work examines the benefits and nuances of a fully inclusive LLM evaluation system. In a detailed case study on emotional intelligence, we deploy a council of 20 recent LLMs to rank each other on open-ended responses to interpersonal conflicts. Our results show that the LMC produces rankings that are more separable and more robust, and through a user study, we show that they are more consistent with human evaluations than any individual LLM judge. Using all LLMs for judging can be costly, however, so we use Monte Carlo simulations and hand-curated sub-councils to study hypothetical council compositions and discuss the value of the incremental LLM judge.