Discourse Diversity in Multi-Turn Empathic Dialogue
LLMs repeat the same empathy tactics. MINT trains models to vary their support strategies across turns while preserving response quality.
Why MINT?
Empathy vs. Diversity Trade-off
MINT achieves the best balance of empathy and diversity across both model sizes.
Explore Conversations
Browse matched conversations from humans, a vanilla LLM, and MINT. The tactic summary below each transcript makes the diversity gap visible at a glance. Human responses are real crowdsourced conversations and may reflect informal or terse phrasing.
I'm feeling so discouraged.. I just got passed over for the promotion I was work…
Want to tag your own conversations? Open the Colab notebook.
I've been feeling so detached from everything lately, like I'm just going throug…
Want to tag your own conversations? Open the Colab notebook.
So, I just lost my job today. I had a sense this was coming, but it's still a sh…
Want to tag your own conversations? Open the Colab notebook.
BibTeX
@article{zhan2026discourse,
title={Discourse Diversity in Multi-Turn Empathic Dialogue},
author={Zhan, Hongli and Gueorguieva, Emma S and Hernandez, Javier and Suh, Jina and Ong, Desmond C and Li, Junyi Jessy},
journal={arXiv preprint arXiv:2604.11742},
year={2026}
}