LLMCheckup：通过可解释性工具和自解释对大型语言模型进行对话式检查
LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
AI总结：
LLMCheckup是一款对话式工具，通过连接多种可解释AI方法，使大型语言模型无需微调即可生成自解释并执行用户意图识别，支持多模态输入与交互式问答，并引入新解析策略提升意图识别准确率。
摘要：
以对话形式提供解释的可解释性工具已证明其在增强用户理解方面的有效性（Slack et al., 2023; Shen et al., 2023），因为一次性解释可能无法向用户提供充足的信息。然而，当前基于对话的解释方案通常需要外部工具和模块，且不易迁移到其未设计针对的任务上。借助LLMCheckup，我们提出了一款易于使用的工具，允许用户与任何最先进的大型语言模型（LLM）就其行为进行对话。我们通过将LLM与广泛的可解释AI（XAI）方法相连接，使其无需微调即可生成解释并执行用户意图识别，这些方法包括特征归因等白盒可解释性工具，以及自解释（例如用于生成理由）。基于LLM的（自）解释以交互式对话的形式呈现，支持后续提问并生成建议。LLMCheckup为系统中可用的操作提供了教程，迎合了XAI领域不同专业水平的用户，并支持多种输入模态。我们引入了一种新的解析策略，大幅提升了LLM的用户意图识别准确率。最后，我们展示了LLMCheckup在事实核查和常识问答任务上的应用。
英文摘要：
Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding (Slack et al., 2023; Shen et al., 2023), as one-off explanations may fall short in providing sufficient information to the user. Current solutions for dialogue-based explanations, however, often require external tools and modules and are not easily transferable to tasks they were not designed for. With LLMCheckup, we present an easily accessible tool that allows users to chat with any state-of-the-art large language model (LLM) about its behavior. We enable LLMs to generate explanations and perform user intent recognition without fine-tuning, by connecting them with a broad spectrum of Explainable AI (XAI) methods, including white-box explainability tools such as feature attributions, and self-explanations (e.g., for rationale generation). LLM-based (self-)explanations are presented as an interactive dialogue that supports follow-up questions and generates suggestions. LLMCheckupprovides tutorials for operations available in the system, catering to individuals with varying levels of expertise in XAI and supporting multiple input modalities. We introduce a new parsing strategy that substantially enhances the user intent recognition accuracy of the LLM. Finally, we showcase LLMCheckup for the tasks of fact checking and commonsense question answering.
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。
