CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking
Therapeutic dialogue is not a sequence of isolated responses: client goals, motivation, resistance, and therapeutic alliance evolve over time. Yet current LLM-based mental health dialogue systems often lack explicit mechanisms for tracking these dynamics across extended interactions, which can lead to poorly timed interventions or premature goal resolution. We introduce CALM-IT, a framework for generating and evaluating long-form Motivational Interviewing dialogues through explicit modeling of evolving client and counselor states, guiding both counseling strategy selection and utterance generation. We evaluate CALM-IT on a large-scale corpus of 8,232 synthetic dialogues spanning multiple dialogue lengths and frameworks. Compared with all baselines, CALM-IT achieves the best performance on most MITI 4.2 global ratings, including Empathy, Partnership, and Softening Sustain Talk, as well as on other key performance metrics while exhibiting minimal performance degradation as dialogue length increases. Notably, although CALM-IT initiates fewer change-directed prompts, it produces the highest client acceptance rate (64.3%) on average across different length conditions. We release a reproducible generation framework, a MITI-grounded process-level evaluation protocol, and a large-scale synthetic corpus for studying therapeutic LLMs under realistic long-form interaction conditions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns…
DiversityImitation LearningThe human longevity record may hold for decades
Since 1990 Jeanne Louise Calment has held the record for human longevity. She was born on 21 February 1875, became the longest-lived human on 12 May 1990 when she was 115.21 and died on 4 August 1997 at age 122.45 years.…
On the Feasibility of Using LLMs to Autonomously Execute Multi-host Network Attacks
LLMs have shown preliminary promise in some security tasks and CTF challenges. Real cyberattacks are often multi-host network attacks, which involve executing a number of steps across multiple hosts such as conducting re…
ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes
The advancement of natural language processing (NLP) systems in healthcare hinges on language model ability to interpret the intricate information contained within clinical notes. This process often requires integrating …
Few-Shot LearningLanguage ModelingLanguage ModellingMambaCalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calcium traces, existing approaches remain task-specific, limiting transfer across…