Newest papers

How Different, or Different How? Stance Granularity in Viewpoint Selection for Dialog Systems that Engage Users with Alternative Views

Morita Tarvirdians, Reeve Lorena, Catharine Oertel · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31459 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

दृष्टिकोण मुख्य रूप से एक स्केलर पैमाने पर प्रतिनिधित्व करते हैं, जो उपयोगकर्ता के साथ अलग-अलग चीजों के बारे में असहमत दृष्टिकोणों को अलग करने के लिए बहुत कठोर हैं। हम एक चयन नीति पेश करते हैं जिसमें एक गुट निर्धारित करता है कि दृष्टिकोण उपयोगकर्ता से कितने दूर बैठ सकते हैं, और नीति उस सीमा के भीतर सबसे नए दृष्टिकोण का चयन करती है। हम केवल अपनी दृष्टिकोण एन्कोडर को तुलना करते हुए एक स्केलर स्कोर को Perspectivized Stance Vectors के साथ तुलना करते हैं, जो अवधारणाओं पर अलग-अलग दृष्टिकोणों में एक स्थिति को तोड़ते हैं। हम इसे एक संवाद प्रणाली के भीतर एकीकृत करते हैं और विषयों के अध्ययन के बीच चलते हैं (N = 63). अवधारणा स्तर की स्थिति

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Viewpoints, Dialog box, Computer science, Selection (genetic algorithm), Human–computer interaction, Granularity

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange