arXiv cs.CL· Morita Tarvirdians, Reeve Lorena, Catharine Oertel·· 13 小时前AI 评分24
对话系统如何选择替代观点？研究对比标量立场与概念级立场编码
How Different, or Different How? Stance Granularity in Viewpoint Selection for Dialog Systems that Engage Users with Alternative Views
AI 导读
研究提出一种基于 bandit 的观点选择策略：由 bandit 设定观点与用户立场的最大距离，再在该范围内选取最新颖的观点，仅改变立场编码器，对比标量分数与 Perspectivized Stance Vectors（将立场拆分为各概念的独立立场）。
正文 · 原文
Abstract:Systems that aim to help a user engage with viewpoints other than their own have to decide how different those viewpoints should be. Viewpoints are mainly represented on a scalar scale, too coarse to distinguish viewpoints that disagree with the user about different things. We introduce a selection policy in which a bandit sets how far viewpoints may sit from the user, and the policy selects the most novel viewpoint within that bound. We vary only its stance encoder, comparing a scalar score with Perspectivized Stance Vectors, which break a position into separate stances on concepts. We integrate it inside a dialog system and run a between-subjects study (N=63). Concept-level stance produces more varied exposure sequences and broader coverage of the topic's positions, but does not change how deeply users justify viewpoints or how accurately they reconstruct them. Finally, we analyze user--viewpoint relations at the concept level, showing that users reconstruct a viewpoint least accurately on concepts that one side took no position on, rather than on concepts where the two disagreed. Our findings open up opportunities for dialog systems that support engagement with alternative viewpoints by acting on which concepts a user and a viewpoint disagree on, rather than on distance alone.
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31459 [cs.HC] |
| (or arXiv:2610.31459v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31459 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Morita Tarvirdians [view email]
[v1]
Thu, 22 Oct 2026 15:52:10 UTC (697 KB)
来源：arXiv cs.CL · arxiv.org