LATIDIA · Robótica

InterSocialBench: Benchmarking Human and LLM Preferences for Companion-Robot Social Behavior

arXiv:2609.15455v1 Tipo de anuncio: nuevo Resumen: Los robots acompañantes se enfrentan a situaciones cotidianas en las que varios comportamientos factibles pueden ser apropiados, pero diferentes personas prefieren respuestas diferentes. Presentamos InterSocialB

La noticia

arXiv:2609.15455v1 Announce Type: new Abstract: Companion robots face everyday situations in which several feasible behaviors may be appropriate, yet different people prefer different responses. We introduce InterSocialBench, a benchmark of 210 domestic scenarios and 18 high-level behaviors, pairing judgments from 100 human participants with 23,520 responses from seven large language models under 16 personality conditions. Each human annotation preserves a preferred action alongside explicitly appropriate and inappropriate candidates. A structured construction pipeline covers behavioral alternatives, competing situational cues, and relevant history and future tasks. Evaluation distinguishes preferred-choice agreement from explicit rejection, using scenario-grouped splits for trainable predictors. Simple frequency and persona-voting baselines illustrate these objectives. Across the tested prompts, model