dorsal/arxiv
View SchemaCALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking
| Authors | Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan, Mary Conlon, Vanessa Rumie, Kristen Risola, Srijan Kumar, Munmun De Choudhury |
|---|---|
| Categories | |
| ArXiv ID | 2601.10085vv1 |
| URL | https://arxiv.org/abs/2601.10085 |
| License | http://creativecommons.org/licenses/by-nc-sa/4.0/ |
Abstract
Large Language Models (LLMs) are increasingly used in mental health-related settings, yet they struggle to sustain realistic, goal-directed dialogue over extended interactions. While LLMs generate fluent responses, they optimize locally for the next turn rather than maintaining a coherent model of therapeutic progress, leading to brittleness and long-horizon drift. We introduce CALM-IT, a framework for generating and evaluating long-form Motivational Interviewing (MI) dialogues that explicitly models dual-actor conversational dynamics. CALM-IT represents therapist-client interaction as a bidirectional state-space process, in which both agents continuously update inferred alignment, mental states, and short-term goals to guide strategy selection and utterance generation. Across large-scale evaluations, CALM-IT consistently outperforms strong baselines in Effectiveness and Goal Alignment and remains substantially more stable as conversation length increases. Although CALM-IT initiates fewer therapist redirections, it achieves the highest client acceptance rate (64.3%), indicating more precise and therapeutically aligned intervention timing. Overall, CALM-IT provides evidence for modeling evolving conversational state being essential for generating high-quality long-form synthetic conversations.
{
"annotation_id": "fe1b3840-50e7-4cae-8dd3-8af56066b414",
"date_created": "2026-02-17T05:53:23.791000Z",
"date_modified": "2026-02-17T05:53:23.791000Z",
"file_hash": "76873eb8383d44bc660f36ec6e05073bcb59bf7d640f6422455d65e4b1f78062",
"private": false,
"record": {
"abstract": "Large Language Models (LLMs) are increasingly used in mental health-related settings, yet they struggle to sustain realistic, goal-directed dialogue over extended interactions. While LLMs generate fluent responses, they optimize locally for the next turn rather than maintaining a coherent model of therapeutic progress, leading to brittleness and long-horizon drift. We introduce CALM-IT, a framework for generating and evaluating long-form Motivational Interviewing (MI) dialogues that explicitly models dual-actor conversational dynamics. CALM-IT represents therapist-client interaction as a bidirectional state-space process, in which both agents continuously update inferred alignment, mental states, and short-term goals to guide strategy selection and utterance generation. Across large-scale evaluations, CALM-IT consistently outperforms strong baselines in Effectiveness and Goal Alignment and remains substantially more stable as conversation length increases. Although CALM-IT initiates fewer therapist redirections, it achieves the highest client acceptance rate (64.3%), indicating more precise and therapeutically aligned intervention timing. Overall, CALM-IT provides evidence for modeling evolving conversational state being essential for generating high-quality long-form synthetic conversations.",
"arxiv_id": "2601.10085",
"authors": [
"Viet Cuong Nguyen",
"Nhi Yen Nguyen",
"Kristin A. Candan",
"Mary Conlon",
"Vanessa Rumie",
"Kristen Risola",
"Srijan Kumar",
"Munmun De Choudhury"
],
"categories": [
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"title": "CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking",
"url": "https://arxiv.org/abs/2601.10085",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f85a231d-c94a-4b6c-a998-0edff36b20c8",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}