CHARP：面向知识 grounded 对话系统的对话历史感知探测
CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
AI总结：
本文提出 CHARP 诊断测试集，用于评估知识 grounded 对话系统的幻觉与对话历史遵从性，发现现有模型因忽略对话历史而表现不佳，并指出 FaithDial 评估的不足。
摘要：
在本工作中，我们深入研究了专注于忠实性的流行知识 grounded 对话基准 FaithDial。我们发现 FaithDial 数据中相当一部分包含注释伪影，这可能使模型偏向于完全忽略对话历史。因此，我们引入了 CHARP，一个诊断性测试集，旨在改进对对话模型中幻觉的评估。CHARP 不仅衡量幻觉，还衡量模型对对话任务的遵从性。我们的广泛分析表明，模型在 CHARP 上表现不佳的主要原因是它们无法有效地关注和推理对话历史。此外，FaithDial 的评估方法未能捕捉这些缺陷，忽视了对话历史。我们的发现表明，在知识 grounded 对话的数据集创建和幻觉评估方面仍有大量贡献空间，CHARP 可以作为监测该特定研究领域进展的工具。CHARP 公开可用，网址为 https://huggingface.co/datasets/huawei-noah/CHARP
英文摘要：
In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a diagnostic test set, designed for an improved evaluation of hallucinations in conversational model. CHARP not only measures hallucination but also the compliance of the models to the conversation task. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. CHARP is publicly available at https://huggingface.co/datasets/huawei-noah/CHARP
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。
