Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations
Jul 1, 2026·,,
,·
1 min read
Mohit Chandra
Siddharth Sriraman
Harneet Singh Khanuja
Yiqiao Jin
Munmun De Choudhury
Abstract
Mental health support over multi-turn conversations stresses LLM reasoning, empathy, and safety in distinct ways. We systematically examine the limits of reasoning-focused LLMs in multi-turn mental health conversations, isolating failure modes that pure reasoning cannot address, and discuss design implications for responsible deployment. ACL 2026 acceptance rate: 19.0%.
Type
Publication
Annual Meeting of the Association for Computational Linguistics (ACL) 2026, Main Conference
Abstract
Mental health support over multi-turn conversations stresses LLM reasoning, empathy, and safety in distinct ways. We systematically examine the limits of reasoning-focused LLMs in multi-turn mental health conversations, isolating failure modes that pure reasoning cannot address.
