评估评估者：衡量LLMs对任务评估指令的遵守情况
Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions
AI总结：
本文研究LLMs在任务评估中的表现，发现提示对评估结果影响有限，困惑度有时比提示更符合人类判断。
摘要：
LLMs-as-a-judge是一种最近流行的方法，它用自动评估代替任务评估中的人类判断（Zheng等人，2024）。由于广泛使用RLHF（基于人类反馈的强化学习），像GPT4和Llama3这样的最先进LLMs在被提示进行质量判断时（如文本的连贯性）预计会与人类偏好有很强的一致性。尽管这似乎是有益的，但不清楚LLMs作为评估者所做出的评估是否仅基于提示中的指令，还是反映了其对高质量数据的偏好，类似于其微调数据。为了调查提示LLMs作为评估者对AI判断与人类判断对齐程度的影响，我们分析了具有不同层次指令的提示，针对几种LLMs-as-a-judge。此外，我们还比较了不使用提示的方法，使用模型的困惑度作为质量度量。我们汇总了在最先进评估中常用的质量标准分类，并将其作为模型作为评估者的严格基准。总体而言，我们显示LLMs-as-a-judge从提示中的高度详细指令中获益甚微，且困惑度有时比提示更能与人类判断一致，尤其是在文本质量方面。
英文摘要：
LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback), state-of-the-art LLMs like GPT4 and Llama3 are expected to have strong alignment with human preferences when prompted for a quality judgement, such as the coherence of a text. While this seems beneficial, it is not clear whether the assessments by an LLM-as-a-judge constitute only an evaluation based on the instructions in the prompts, or reflect its preference for high-quality data similar to its fine-tune data. To investigate how much influence prompting the LLMs-as-a-judge has on the alignment of AI judgements to human judgements, we analyze prompts with increasing levels of instructions about the target quality of an evaluation, for several LLMs-as-a-judge. Further, we compare to a prompt-free method using model perplexity as a quality measure instead. We aggregate a taxonomy of quality criteria commonly used across state-of-the-art evaluations with LLMs and provide this as a rigorous benchmark of models as judges. Overall, we show that the LLMs-as-a-judge benefit only little from highly detailed instructions in prompts and that perplexity can sometimes align better with human judgements than prompting, especially on textual quality.
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。
