paper-with-me

Papers

CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking

2026-01-15 · Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan, Mary Conlon, Vanessa Rumie, Kristen Risola, Michael L. Birnbaum, Munmun De Choudhury arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.10085

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CALM: Conditional Adversarial Latent Models for Directable Virtual Characters

2023-05-02 · Chen Tessler, Yoni Kasten, Yunrong Guo, Shie Mannor 외

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 Learning

The human longevity record may hold for decades

2018-09-11

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

2025-01-27 · Brian Singer, Keane Lucas, Lakshmi Adiga, Meghna Jain 외

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

2024-03-09 · Zhichao Yang, Avijit Mitra, Sunjae Kwon, Hong Yu

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 ModellingMamba

CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data

2026-04-03 · Xinhong Xu, Yimeng Zhang, Qichen Qian, Yuanlong Zhang arxiv

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…