cs.HC · 2026-08-27 · No. 97

Human-Computer Interaction, 2026-08-27.

3 new papers in cs.HC. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

3 entries
  1. 01

    Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferences

    Natasha Ureyang, Sebastian Porsdam Mann, Yuxin Liu, Zuriel Hassirim, Melanie Almonte, Wenhao Chen, Joyce Ng, Thant...

    cs.HC · cs.LG

    In serious illness, human surrogates often struggle to accurately predict patient preferences (68% accuracy), causing decision conflict. Personalized Patient Preference Predictor (P4) agents offer a potential solution, but prior prototypes treat values as static ratings, ignoring the contextual, situation-dependent nature of medical choices. Grounded in the 'logic of care', we present P4-DT (Dilemma Training), a P4 agent that constructs a...

    arxiv.org/abs/2608.25771 · PDF

  2. 02

    Are Concept Bottleneck Models Effective as Decision-Support Systems?

    Alessandro Bogani, Nicola Debole, Emanuele Marconato, Andrea Pugnana, Katya Tentori, Andrea Passerini

    cs.HC · cs.AI

    Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allowing users to inspect the concepts underlying a prediction and explore how predictions change under alternative concept configurations, CBMs have emerged as one of the most prominent approaches to supporting human-AI collaboration. However, user studies investigating...

    arxiv.org/abs/2608.25581 · PDF

  3. 03

    Q&A or Document-Based? The Effects of Interface Type on How Screen Reader Users Access Interconnected Documents

    Colleen F. Cipriano, Yichun Zhao, Miguel A. Nacenta, Kotaro Hara, Jaylee Soh

    cs.HC · cs.AI · cs.IR

    Blind and low-vision (BLV) users are increasingly engaging with large language model (LLM) interfaces to access documents, but it is unclear how such systems support or hinder their ability to build interconnected knowledge. To examine this gap, we compared a Question-Answer Interface (QAI) that supports open-ended conversational inquiry, with a Document Interface (DI) based mostly on traditional structured text document navigation. We...

    arxiv.org/abs/2608.25382 · PDF

This edition is part of The Daily Abstract — cs.HC archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.