arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.00543cs.CL
收藏

评估大语言模型评估器的一致性

Evaluating the Consistency of LLM Evaluators

KAIST AI(韩国科学技术院人工智能学院)

Noah Lee, Jiwoo Hong, James Thorne

AI总结:

针对LLM评估器一致性研究不足的问题,本文对其自一致性和跨尺度一致性在不同评分尺度、标准粒度及模型类型下开展广泛研究,发现强专有模型未必是一致评估器,强调了一致性对评估LLM评估器能力的重要性。

摘要:

大语言模型(LLMs)作为通用评估器展现出潜力,同时具备速度和成本方面的显著优势。尽管其与人类标注者的相关性已被广泛研究,但作为评估器的一致性仍未得到充分关注,这引发了对LLM评估器可靠性的担忧。本文针对LLM评估一致性的两个方面——自一致性(SC)和跨尺度一致性(IC),在不同评分尺度和标准粒度下,使用开源和专有模型开展了广泛研究。我们的综合分析表明,性能强大的专有模型未必是一致性良好的评估器,凸显了在评估LLM评估器能力时考虑一致性的重要性。

英文摘要:

Large language models (LLMs) have shown potential as general evaluators along with the evident benefits of speed and cost. While their correlation against human annotators has been widely studied, consistency as evaluators is still understudied, raising concerns about the reliability of LLM evaluators. In this paper, we conduct extensive studies on the two aspects of consistency in LLM evaluations, Self-Consistency (SC) and Inter-scale Consistency (IC), on different scoring scales and criterion granularity with open-source and proprietary models. Our comprehensive analysis demonstrates that strong proprietary models are not necessarily consistent evaluators, highlighting the importance of considering consistency in assessing the capability of LLM evaluators.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑