Work

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

Year: 2026
Type: article
Abstract: 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. Results favored the affect-aware condition on key perceived qualities of the interaction, particularly emotional intelligence and mood responsiveness. These findings suggest that real-time affective context may add relational grounding to LLM conversations without reducing usability or eliciting uncanny-like perceptions.
Language: English
Open Access status: green
OpenAlex ID: W7166591347
FWCI:
Cites: 24
Cited by:
Related to: 10