Jina Suh
2 papers · Latest:
Natural Language Processing
Discourse Diversity in Multi-Turn Empathic Dialogue
This paper introduces MINT, an RL framework that significantly improves discourse diversity and empathy in multi-turn LLM conversations by reducing tactic repetition.
2604.11742
Natural Language ProcessingAI generates well-liked but templatic empathic responses
AI-generated empathic responses are well-liked but highly formulaic, consistently deploying a specific template unlike diverse human replies.
2604.08479
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.