当哈利遇见超人：对话者角色在基于人设的对话生成中的作用
When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
AI总结：
本研究探讨了对话者人设信息对基于人设的对话生成的影响，通过作者识别任务评估模型在双人设对齐、熟悉度鲁棒性及微调上的表现，发现获取对话者人设能提升识别效果，但模型在处理不熟悉对话者时仍有困难。
摘要：
赋予对话智能体人设信息已被证明能显著提升其生成内容的一致性与多样性。尽管已有大量研究关注使对话与给定人设保持一致，但对对话者档案的适应仍 largely underexplored。在本研究中，我们调查了三个关键方面：（1）模型将回复与给定人设及对话者人设对齐的能力；（2）其在处理熟悉与不熟悉的对话者和话题时的鲁棒性；（3）在特定基于人设的对话上进行额外微调的影响。我们评估了使用多样化说话人配对和话题生成的对话，将评估构建为作者识别任务，并采用 LLM-as-a-judge 和人工评估。通过系统地掩盖或披露关于对话者的信息，我们评估其对对话生成的影响。结果显示，获取对话者的人设能改善对目标说话人的识别，而掩盖人设则产生相反效果。尽管模型在跨话题上泛化良好，但在处理不熟悉的对话者时会遇到困难。最后，我们发现，在零样本设置下，LLM 经常复制传记细节，这虽然促进了识别，但使任务变得 trivial。
英文摘要：
Endowing dialogue agents with persona information has proven to significantly improve the consistency and diversity of their generations. While much focus has been placed on aligning dialogues with provided personas, the adaptation to the interlocutor's profile remains largely underexplored. In this work, we investigate three key aspects: (1) a model's ability to align responses with both the provided persona and the interlocutor's; (2) its robustness when dealing with familiar versus unfamiliar interlocutors and topics, and (3) the impact of additional fine-tuning on specific persona-based dialogues. We evaluate dialogues generated with diverse speaker pairings and topics, framing the evaluation as an author identification task and employing both LLM-as-a-judge and human evaluations. By systematically masking or disclosing information about the interlocutor, we assess its impact on dialogue generation. Results show that access to the interlocutor's persona improves the recognition of the target speaker, while masking it does the opposite. Although models generalise well across topics, they struggle with unfamiliar interlocutors. Finally, we found that in zero-shot settings, LLMs often copy biographical details, facilitating identification but trivialising the task.
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。
