大语言模型作为评估者时的认知偏差基准测试
Benchmarking Cognitive Biases in Large Language Models as Evaluators
AI总结：
本研究提出CoBBLEr基准，测试15个LLM作为评估器时的6种认知偏差，发现其平均偏差率达40%，且机器与人类偏好的平均RBO分数仅49.6%，表明LLM目前无法可靠替代人类进行自动标注。
摘要：
大语言模型是存在认知偏差的评判者。近期研究表明，大语言模型（LLM）通过简单的提示和上下文学习，可作为有效的自动评估器。在本研究中，我们汇集了4种不同规模范围的15个LLM，并通过其他LLM作为评估器（例如“系统Star优于系统Square”）的偏好排序来评估它们的输出响应。随后，我们通过引入“LLM作为评估器的认知偏差基准”（CoBBLEr）来评估排序输出的质量，这是一个用于衡量LLM评估输出中6种不同认知偏差的基准，例如模型在评估时倾向于将自身输出排名靠前的自我中心偏差。我们发现，LLM是有偏差的文本质量评估器，在每个评估中均在我们的偏差基准上表现出强烈的偏差迹象（所有模型平均40%的比较结果），这对其作为评估器的稳健性提出了质疑。此外，我们检验了人类与机器偏好之间的相关性，并计算出平均排序偏差重叠（RBO）分数为49.6%，表明机器偏好与人类不一致。根据我们的发现，LLM可能仍无法用于与人类偏好对齐的自动标注。我们的项目页面位于：https://minnesotanlp.github.io/cobbler。
英文摘要：
Large Language Models are cognitively biased judges. Large Language Models (LLMs) have recently been shown to be effective as automatic evaluators with simple prompting and in-context learning. In this work, we assemble 15 LLMs of four different size ranges and evaluate their output responses by preference ranking from the other LLMs as evaluators, such as System Star is better than System Square. We then evaluate the quality of ranking outputs introducing the Cognitive Bias Benchmark for LLMs as Evaluators (CoBBLEr), a benchmark to measure six different cognitive biases in LLM evaluation outputs, such as the Egocentric bias where a model prefers to rank its own outputs highly in evaluation. We find that LLMs are biased text quality evaluators, exhibiting strong indications on our bias benchmark (average of 40% of comparisons across all models) within each of their evaluations that question their robustness as evaluators. Furthermore, we examine the correlation between human and machine preferences and calculate the average Rank-Biased Overlap (RBO) score to be 49.6%, indicating that machine preferences are misaligned with humans. According to our findings, LLMs may still be unable to be utilized for automatic annotation aligned with human preferences. Our project page is at: https://minnesotanlp.github.io/cobbler.
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。
