[论文解读] Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Yang Liu, Yuanshun Yao+7 more|arXiv (Cornell University)|Aug 10, 2023

Topic Modeling被引用 69

一句话总结

本综述提出了覆盖七个可信度类别的LLM对齐的细粒度分类法，并提供评估指南和案例研究，展示对齐如何影响整体可信度。

ABSTRACT

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications.

研究动机与目标

• 识别与对齐相关的LLM可信度的关键维度。
• 提出一个包含29个子类别的细粒度分类法，用于全面评估。
• 提供多目标评估LLM可信度的指南和数据集。
• 展示测量研究，显示对齐在不同模型中的影响。
• 强调在可靠部署中对齐LLMs的机遇与挑战。

提出的方法

• 提出一个涵盖七大类的分类法（可靠性、安全性、公平性、抗滥用性、可解释性与推理、社会规范、鲁棒性），共29个子类别。
• 回顾文献与现有风险，以证成该分类法。
• 概述多目标对齐评估的评估任务与数据集构建原则。
• 对广泛使用的LLM进行测量研究，以评估选定子类别下的对齐情况。
• 演示如何将生成的评估数据重新用于对齐改进。
• 提供指南和案例研究，说明数据集设计与评估工作流。

实验结果

研究问题

• RQ1 在可信部署中，LLM对齐的关键维度和子类别是什么？
• RQ2 如何构建评估数据集，以在各类别中实现对LLM可信度的多目标评估？
• RQ3 更多对齐的模型是否在所有类别中都能持续提升可信度？对齐收益在哪些方面有变化？

主要发现

• 提出了一个细粒度分类法，包括七大类和29个子类别，用于指导LLM对齐的评估。
• 测量研究表明，通常更多对齐的模型在总体可信度上表现更好，但效果因类别而异。
• 评估数据集和模板化提示生成可用于执行多目标对齐并指导有针对性的改进。
• 对齐的模型并不在所有类别上普遍提升，需要进行针对类别的评估与改进。
• 本文提供了支持全面对齐评估的数据收集的实用指南。
• 评估管线也可以作为对齐任务的数据生成器。