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

• URL: http://arxiv.org/abs/2406.08598v3
• Date: Tue, 11 Feb 2025 18:42:44 GMT
• Title: Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks
• Authors: Justin Zhao, Flor Miriam Plaza-del-Arco, Benjie Genchel, Amanda Cercas Curry,
• Abstract summary: 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. 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.
• Score: 3.58262772907022
• License:
• 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.

Related papers

• The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs [21.97227334180969]
  "LLM-as-a-judge" paradigm employs Large Language Models as annotators and evaluators in tasks traditionally performed by humans. Despite their role in shaping study results and insights, there is no standard or rigorous procedure to determine whether LLMs can replace human annotators. We propose a novel statistical procedure -- the Alternative Annotator Test (alt-test) -- that requires only a modest subset of annotated examples to justify using LLM annotations.
  arXiv  Detail & Related papers  (2025-01-19T07:09:11Z)
• Observing Micromotives and Macrobehavior of Large Language Models [14.649811719084505]
  We follow Schelling's model of segregation to observe the relationship between the micromotives and macrobehavior of large language models. Our results indicate that, regardless of the level of bias in LLMs, a highly segregated society will emerge as more people follow LLMs' suggestions.
  arXiv  Detail & Related papers  (2024-12-10T23:25:14Z)
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods [21.601196380989542]
  ''LLMs-as-judges'' are evaluators based on natural language responses. This paper presents a comprehensive survey of the ''LLMs-as-judges'' paradigm from five key perspectives. We aim to provide insights on the development and application of ''LLMs-as-judges'' in both research and practice.
  arXiv  Detail & Related papers  (2024-12-07T08:07:24Z)
• Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions [77.66677127535222]
  Auto-Arena is an innovative framework that automates the entire evaluation process using LLM-powered agents. In our experiments, Auto-Arena shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks.
  arXiv  Detail & Related papers  (2024-05-30T17:19:19Z)
• DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators. The question of how reliable these evaluators are has emerged as a crucial research question. We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models [56.02275285521847]
  We propose to evaluate models using a Panel of LLm evaluators (PoLL) We find that using a PoLL composed of a larger number of smaller models outperforms a single large judge, exhibits less intra-model bias due to its composition of disjoint model families, and does so while being over seven times less expensive.
  arXiv  Detail & Related papers  (2024-04-29T15:33:23Z)
• PRE: A Peer Review Based Large Language Model Evaluator [14.585292530642603]
  Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs. We propose a novel framework that can automatically evaluate LLMs through a peer-review process.
  arXiv  Detail & Related papers  (2024-01-28T12:33:14Z)
• Evaluating Large Language Models at Evaluating Instruction Following [54.49567482594617]
  We introduce a challenging meta-evaluation benchmark, LLMBar, designed to test the ability of an LLM evaluator in discerning instruction-following outputs. We discover that different evaluators exhibit distinct performance on LLMBar and even the highest-scoring ones have substantial room for improvement.
  arXiv  Detail & Related papers  (2023-10-11T16:38:11Z)
• PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations [10.709365940160685]
  Modern large language models (LLMs) are hard to evaluate and compare automatically. We propose a peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs. We find that our approaches achieve higher accuracy and align better with human judgments.
  arXiv  Detail & Related papers  (2023-07-06T04:05:44Z)
• On Learning to Summarize with Large Language Models as References [101.79795027550959]
  Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
  arXiv  Detail & Related papers  (2023-05-23T16:56:04Z)
• Benchmarking Large Language Models for News Summarization [79.37850439866938]
  Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. We find instruction tuning, and not model size, is the key to the LLM's zero-shot summarization capability.
  arXiv  Detail & Related papers  (2023-01-31T18:46:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.