arXiv：cs.AI· Jasper Dekoninck, Maximilian Baader, Martin Vechev·· 5 小时前
Polyrating：面向 LLM 评估的高性价比偏差感知评分系统
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
AI 导读
Polyrating 是一个基于最大后验估计的 LLM 评分系统，可检测并量化影响人类偏好的偏差，实现更公平的模型比较。它借助已有 benchmark 分数，将新模型的人工评估成本最多降低 41%，新任务最多降低 77%，并支持跨任务直接比较评分。
正文
Abstract:Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current rating systems suffer from several important limitations: first, they fail to account for biases that significantly influence evaluation results, second, they require large and expensive preference datasets to obtain accurate ratings, and third, they do not facilitate meaningful comparisons of model ratings across different tasks. To address these issues, we introduce Polyrating, an expressive and flexible rating system based on maximum a posteriori estimation that enables a more nuanced and thorough analysis of model performance at lower costs. Polyrating can detect and quantify biases affecting human preferences, ensuring fairer model comparisons. Further, Polyrating can reduce the cost of human evaluations by up to $41\%$ for new models and up to $77\%$ for new tasks by leveraging existing benchmark scores. Lastly, Polyrating enables direct comparisons of ratings across different tasks, providing a comprehensive understanding of an LLMs' strengths, weaknesses, and relative performance across different applications.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2409.00696 [cs.CL] |
| (or arXiv:2409.00696v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2409.00696 arXiv-issued DOI via DataCite |
Submission history
From: Jasper Dekoninck [view email]
[v1]
Sun, 1 Sep 2024 11:24:54 UTC (1,865 KB)
[v2]
Mon, 14 Oct 2024 10:01:33 UTC (1,847 KB)
[v3]
Tue, 11 Feb 2025 12:21:13 UTC (2,012 KB)
[v4]
Mon, 12 Oct 2026 10:32:26 UTC (1,289 KB)
来源：arXiv：cs.AI · arxiv.org