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

DOI: 10.48550/arXiv.2610.31459 · open-access PDF

Spanish

Los sistemas que tienen como objetivo ayudar a un usuario a interactuar con puntos de vista distintos de los propios tienen que decidir cuán diferentes deben ser esos puntos de vista. Los puntos de vista están representados principalmente en una escala escalar, demasiado gruesos para distinguir puntos de vista que no están de acuerdo con el usuario sobre cosas diferentes. Introducimos una política de selección en la que un bandido establece cuán lejos pueden estar los puntos de vista del usuario, y la política selecciona el punto de vista más nuevo dentro de ese límite. Sólo variamos su codificador de postura, comparando una puntuación escalar con Perspectivized Stance Vectors, que dividen una posición en posiciones separadas sobre conceptos.

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 integr

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31459, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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