arXiv:2606.18256v1 Announce Type: cross Abstract: LLM-based chatbots are increasingly applied in interpersonal domains such as counseling and peer support, where establishing human-AI rapport is crucial yet remains challenging. In this work, we introduce a novel approach for conditioning LLMs with in-group personas, which (i) first identifies a user's primary concern and brief personal context (e.g., a computer science undergraduate worried about future career prospects), and (ii) generates a synthetic in-group persona that shares a similar primary concern while differing in background and nar
The increasing application of LLMs in sensitive interpersonal domains necessitates improved human-AI rapport, which current models struggle to achieve.
Enhancing rapport allows AI to be more effective in critical human-facing applications, expanding its utility in previously challenging sectors.
AI systems can now be dynamically conditioned to generate personas that foster empathy and connection with users based on their specific concerns.
- · AI developers
- · Therapy and counseling platforms
- · Customer service industries
- · Mental health support services
- · Generic chatbot providers
- · Companies relying solely on static AI personas
More effective and empathetic AI interactions in sensitive fields.
Increased user trust and adoption of AI for personal support and guidance.
Ethical considerations around the manipulation of human emotions and the potential for over-reliance on AI for emotional support.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI