Affect-aware human-agent conversations: towards empathic LLM interaction

Micro and Nano Systems Letters · Springer Nature · 2026-11-17 · DOI: 10.1007/s12652-026-05141-z

Аннотация

Large Language Models can produce supportive responses, but their apparent empathic behavior is usually grounded only in explicit textual input. This paper presents Empathic Extended Prompting , a real-time affect-aware framework that enriches human–LLM conversation with facial affective descriptors to support perceived empathic attunement. The system integrates FaceReader-based affective descriptors into the LLM context, including emotional intensity, valence, and arousal. We evaluated the approach in a within-subjects study with $$N=20$$ participants, comparing an affect-aware experimental condition with an empathic text-only baseline. Exploratory item-level results and forced-choice preferences favored the affect-aware condition on specific interactional facets. These preliminary findings suggest that real-time affective context may add relational grounding to LLM conversations without reducing usability.

Читать у издателя →

Похожие статьи