arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2309.13633cs.HCcs.AIcs.CL
收藏

EvalLM:基于用户定义标准的大型语言模型提示交互式评估

EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria

KAIST(韩国科学技术院);NAVER AI Lab(NAVER AI实验室)

Tae Soo Kim, Yoonjoo Lee, Jamin Shin, Young-Ho Kim, Juho Kim

AI总结:

EvalLM是一个交互式系统,让用户用自然语言定义标准并利用LLM评估器迭代优化提示,实验表明相比手动评估可检查两倍输出并以少59%的修改次数达到满意提示。

摘要:

通过简单地编写提示,开发者可以利用大型语言模型(LLMs)原型化新颖的生成式应用。然而,为了将原型细化为产品,开发者必须通过评估输出来诊断弱点,从而迭代地修改提示。形成性访谈(N=8)显示,开发者在评估上下文特定和主观标准时,投入了大量精力进行手动输出评估。我们提出了EvalLM,这是一个交互式系统,用于通过基于用户定义的标准评估多个输出来迭代地细化提示。用户可以用自然语言描述标准,利用系统的基于LLM的评估器获得提示在哪些方面表现良好或失败的概览,并根据评估器的反馈改进这些提示。一项比较研究(N=12)表明,与手动评估相比,EvalLM帮助参与者编写了更多样化的标准,检查了两倍数量的输出,并以少59%的修改次数达到令人满意的提示。除了提示之外,我们的工作还可以扩展到特定应用场景中的模型评估和对齐。

英文摘要:

By simply composing prompts, developers can prototype novel generative applications with Large Language Models (LLMs). To refine prototypes into products, however, developers must iteratively revise prompts by evaluating outputs to diagnose weaknesses. Formative interviews (N=8) revealed that developers invest significant effort in manually evaluating outputs as they assess context-specific and subjective criteria. We present EvalLM, an interactive system for iteratively refining prompts by evaluating multiple outputs on user-defined criteria. By describing criteria in natural language, users can employ the system's LLM-based evaluator to get an overview of where prompts excel or fail, and improve these based on the evaluator's feedback. A comparative study (N=12) showed that EvalLM, when compared to manual evaluation, helped participants compose more diverse criteria, examine twice as many outputs, and reach satisfactory prompts with 59% fewer revisions. Beyond prompts, our work can be extended to augment model evaluation and alignment in specific application contexts.

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。

↑