发表机构
The University of Electro-Communications（东京电机大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对AI辅助文本咨询中咨询师行为与对话质量关联的未知问题，基于KokoroChat数据集分析发现肯定比反思更与咨询质量相关，且该信号可迁移至ESConv数据集，为相关培训和系统设计提供经验依据。
AI 中文摘要
尽管人工智能辅助的基于文本的咨询正受到关注，但从经验上看，哪些咨询师行为与更高的对话质量相关仍不清楚。现有研究往往高度聚焦于反思（Reflection），借鉴动机性访谈（Motivational Interviewing）的框架。为解决这一差距，我们使用KokoroChat开展多层分析，KokoroChat是一个由专业咨询师和实习生开展的大规模日语文本咨询数据集，新添加了咨询师策略标签和来访者痛苦程度的标注。我们的结果表明，在本研究使用的质量指标下，在所分析的策略中，肯定（Affirmation）比反思（Reflection）与会话质量的关联更一致。跨数据集迁移实验进一步表明，这种质量信号在ESConv（一个包含非专业支持者的英语数据集）上也能在一定程度上被观察到。这些发现为咨询师培训和情感支持系统设计提供了经验启示。我们在该网址发布了额外的KokoroChat标注和实验源代码。
英文摘要
While AI-assisted text-based counseling is gaining attention, it remains empirically unclear which counselor behaviors are associated with higher dialogue quality. Existing research often focuses heavily on Reflection, borrowing frameworks from Motivational Interviewing. To address this gap, we conduct a multi-layered analysis using KokoroChat, a large-scale Japanese text counseling dataset conducted by professional counselors and trainees, newly annotated with counselor strategy tags and client distress levels. Our results show that, under the quality indicators used in this study, Affirmation is more consistently associated with session quality than Reflection among the analyzed strategies. Cross-dataset transfer experiments further suggest that this quality signal can be observed to some extent on ESConv, an English dataset with non-expert supporters. These findings provide empirical implications for counselor training and emotional support system design. We release the additional KokoroChat annotations and experimental source code at https://github.com/UEC-InabaLab/BeyondReflection.
CommentsAccepted to EMNLP 2026 Findings
