---
title: "StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation"
description: "The framework first builds client profiles from the DSM-5 cross-cutting symptom questionnaire, where an LLM assigns item… 44 references."
authors: ["Qingyu Meng", "Min Chen", "Dingming Liu", "Yifan Mo", "Yue Su", "Xin Sun", "Koen Hindriks", "Jiahuan Pei"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.468/"
doi: "10.18653/v1/2026.findings-acl.468"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/meng-2026-storymi-steerable-multi-agent-therapeutic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/meng-2026-storymi-steerable-multi-agent-therapeutic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/17/) / StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

# StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

**Authors:** Qingyu Meng, [Min Chen](https://md.research.elamur.ai/free/en/authors/min-chen/), Dingming Liu, Yifan Mo, Yue Su, [Xin Sun](https://md.research.elamur.ai/free/en/authors/xin-sun/), Koen Hindriks and Jiahuan Pei · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.468/) · [PDF](https://aclanthology.org/2026.findings-acl.468.pdf) · [DOI 10.18653/v1/2026.findings-acl.468](https://doi.org/10.18653/v1/2026.findings-acl.468) · [OpenAlex](https://openalex.org/W7166853454)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
StoryMI targets three weaknesses of LLM-generated motivational interviewing (MI) dialogues: client personas lack concrete situational context, counseling strategy cannot be steered across turns, and standard metrics overlook clinical strategy. The framework first builds client profiles from the DSM-5 cross-cutting symptom questionnaire, where an LLM assigns item severities and short first-person rationales. It then turns each profile into a roughly 200-word situational story. Three agents run the conversation. Client and therapist agents produce utterances tagged with MI codes. An interaction manager tracks a shared dialogue state, chooses the therapist's next MI code based on the recent code history, and decides when the session ends. The evaluation combines lexical metrics, MI-specific measures of macro-level strategy, LLM judges and expert ratings. The authors report that story grounding and strategy-level control improve MI adherence and clinical plausibility. They also find that LLM judges handle structural qualities well but miss empathy and naturalness. This motivates hybrid evaluation and offers a reproducible resource for research on psychotherapy dialogue.

## Key points
- The released dataset contains 6,000 simulated MI dialogues built from 1,000 questionnaire–story pairs, covering 12 MI codes and 13 DSM-5 symptom domains (23 questionnaire items). Code and data are on GitHub (Beren-sds/StoryMI).
- Six open- and closed-source LLMs are benchmarked within the same multi-agent workflow.
- Two LLM judges, GLM-5 and GPT-5-Nano, were compared against human ratings. GLM-5 correlated better with humans on 4 of 6 dimensions, for example Progress (r ≈ 0.54 vs. 0.43). On Naturalness, GPT-5-Nano's correlation was near zero (r ≈ 0.01), while GLM-5's was weak but significant (ρ ≈ 0.22).
- Models that asked more open questions received higher human empathy ratings. Different strategy profiles, either question-heavy or reflection-heavy, reached comparable human-rated quality.
- Stated limitations:
  - The work covers MI only.
  - Validation relies on expert annotation, with no real clients involved.
  - DSM-5 profiling carries a Western bias and limits persona diversity.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tokyo Institute of Technology](https://md.research.elamur.ai/free/en/universities/tokyo-institute-of-technology/) — University, Tokyo, Japan · 22 works · 2,137 citations
- [Vrije Universiteit Amsterdam](https://md.research.elamur.ai/free/en/universities/vrije-universiteit-amsterdam/) — University, Amsterdam, Netherlands · 42 works · 3,372 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works · [💭 Applied Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/applied-psychology/) · 21 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works

## Cite

Cite as: Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks and Jiahuan Pei. 2026. StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{meng2026storymi,
  title = {{StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation}},
  author = {Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks and Jiahuan Pei},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.468},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.468}
}
```

- [← previous Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification](https://md.research.elamur.ai/free/en/papers/phu-2026-stochastic-gradient-descenders-semeval-2026/)
- [next → Streaming Hallucination Detection in Long Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/lu-2026-streaming-hallucination-detection-long-chain/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/17/)

## References

44 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12930–12949. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+12930%E2%80%9312949%2E+Association+for+Computational+Linguistics%2E)
2. Ron Artstein and Massimo Poesio. 2008. Inter-coder agreement for computational linguistics. Computational Linguistics, pages 555–596. [find](https://scholar.google.com/scholar?q=Ron+Artstein+and+Massimo+Poesio%2E+2008%2E+Inter%2Dcoder+agreement+for+computational+linguistics%2E+Computational+Linguistics%2C+pages+555%E2%80%93596%2E)
3. Erkan Basar, Xin Sun, Iris Hendrickx, Jan de Wit, Tibor Bosse, Gert-Jan De Bruijn, Jos A. Bosch, and Emiel Krahmer. 2025. How well can large language models reflect? A human evaluation of LLM-generated reflections for motivational interviewing dialogues. In Proceedings of the 31st International Conf… [find](https://scholar.google.com/scholar?q=Erkan+Basar%2C+Xin+Sun%2C+Iris+Hendrickx%2C+Jan+de+Wit%2C+Tibor+Bosse%2C+Gert%2DJan+De+Bruijn%2C+Jos+A%2E+Bosch%2C+and+Emiel+Krahmer%2E+2025%2E+How+well+can+large+language+models+reflect%3F+A+human+evaluation+of+LLM%2Dgenerate)
4. Daniel Cabrera Lozoya, Eloy Hernandez Lua, Juan Alberto Barajas Perches, Mike Conway, and Simon D’Alfonso. 2025. Synthetic empathy: Generating and evaluating artificial psychotherapy dialogues to detect empathy in counseling sessions. In Proceedings of the 10th Workshop on Computational Linguistics… [find](https://scholar.google.com/scholar?q=Daniel+Cabrera+Lozoya%2C+Eloy+Hernandez+Lua%2C+Juan+Alberto+Barajas+Perches%2C+Mike+Conway%2C+and+Simon+D%E2%80%99Alfonso%2E+2025%2E+Synthetic+empathy%3A+Generating+and+evaluating+artificial+psychotherapy+dialogues+to+dete)
5. Siyuan Chen, Mengyue Wu, Kenny Q. Zhu, Kunyao Lan, Zhiling Zhang, and Lyuchun Cui. 2023. LLM-empowered chatbots for psychiatrist and patient simulation: Application and evaluation. Preprint, arXiv:2305.13614. — [arXiv:2305.13614](https://arxiv.org/abs/2305.13614) [find](https://scholar.google.com/scholar?q=Siyuan+Chen%2C+Mengyue+Wu%2C+Kenny+Q%2E+Zhu%2C+Kunyao+Lan%2C+Zhiling+Zhang%2C+and+Lyuchun+Cui%2E+2023%2E+LLM%2Dempowered+chatbots+for+psychiatrist+and+patient+simulation%3A+Application+and+evaluation%2E+Preprint%2C+arXiv%3A230)
6. Yu Ying Chiu, Ashish Sharma, Inna Wanyin Lin, and Tim Althoff. 2024. A computational framework for behavioral assessment of LLM therapists. Preprint, arXiv:2401.00820. — [arXiv:2401.00820](https://arxiv.org/abs/2401.00820) [find](https://scholar.google.com/scholar?q=Yu+Ying+Chiu%2C+Ashish+Sharma%2C+Inna+Wanyin+Lin%2C+and+Tim+Althoff%2E+2024%2E+A+computational+framework+for+behavioral+assessment+of+LLM+therapists%2E+Preprint%2C+arXiv%3A2401%2E00820%2E+%E2%80%94+%5BarXiv%3A2401%2E00820%5D%28https%3A%2F%2Farx)
7. Nouha Dziri, Ehsan Kamalloo, Kory Mathewson, and Osmar Zaiane. 2019. Evaluating coherence in dialogue systems using entailment. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3806–3812. Associat… [find](https://scholar.google.com/scholar?q=Nouha+Dziri%2C+Ehsan+Kamalloo%2C+Kory+Mathewson%2C+and+Osmar+Zaiane%2E+2019%2E+Evaluating+coherence+in+dialogue+systems+using+entailment%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapter+of+t)
8. Michael B First. 2024. DSM-5-TR Handbook of Differential Diagnosis. American Psychiatric Association Publishing. [find](https://scholar.google.com/scholar?q=Michael+B+First%2E+2024%2E+DSM%2D5%2DTR+Handbook+of+Differential+Diagnosis%2E+American+Psychiatric+Association+Publishing%2E)
9. Silin Gao, Beatriz Borges, Soyoung Oh, Deniz Bayazit, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, and Antoine Bosselut. 2023. PeaCoK: Persona commonsense knowledge for consistent and engaging narratives. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pages… [find](https://scholar.google.com/scholar?q=Silin+Gao%2C+Beatriz+Borges%2C+Soyoung+Oh%2C+Deniz+Bayazit%2C+Saya+Kanno%2C+Hiromi+Wakaki%2C+Yuki+Mitsufuji%2C+and+Antoine+Bosselut%2E+2023%2E+PeaCoK%3A+Persona+commonsense+knowledge+for+consistent+and+engaging+narrative)
10. Brian Hyeongseok Kim and Chao Wang. 2025. Large language models for interpretable mental health diagnosis. Preprint, arXiv:2501.07653. — [arXiv:2501.07653](https://arxiv.org/abs/2501.07653) [find](https://scholar.google.com/scholar?q=Brian+Hyeongseok+Kim+and+Chao+Wang%2E+2025%2E+Large+language+models+for+interpretable+mental+health+diagnosis%2E+Preprint%2C+arXiv%3A2501%2E07653%2E+%E2%80%94+%5BarXiv%3A2501%2E07653%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2501%2E07653%29)
11. Hyunwoo Kim, Jack Hessel, Liwei Jiang, Peter West, Ximing Lu, Youngjae Yu, Pei Zhou, Ronan Bras, Malihe Alikhani, Gunhee Kim, Maarten Sap, and Yejin Choi. 2023. [SODA: Million-scale dialogue distillation with social commonsense contextualization](https://md.research.elamur.ai/free/en/papers/kim-2023-soda-million-scale-dialogue-distillation/).
12. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [CAMEL: Communicative agents for "mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). In Advances in Neural Information Processing Systems, volume 36, pages 51991–52008. Curran Associates, Inc.
13. Qintong Li, Piji Li, Zhaochun Ren, Pengjie Ren, and Zhumin Chen. 2022. Knowledge bridging for empathetic dialogue generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10993–11001. AAAI Press. [find](https://scholar.google.com/scholar?q=Qintong+Li%2C+Piji+Li%2C+Zhaochun+Ren%2C+Pengjie+Ren%2C+and+Zhumin+Chen%2E+2022%2E+Knowledge+bridging+for+empathetic+dialogue+generation%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+3)
14. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. [G-eval: NLG evaluation using GPT-4 with better human alignment](https://md.research.elamur.ai/free/en/papers/liu-2023-g-eval-nlg-evaluation-gpt/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2511–2522. Association for Computational Linguistics.
15. Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. [MIME: MIMicking emotions for empathetic response generation](https://md.research.elamur.ai/free/en/papers/majumder-2020-mime-mimicking-emotions-empathetic-response/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8968–…
16. William R. Miller. 2000. Motivational Interviewing Skill Code (MISC) Coder’s Manual. Unpublished manuscript. Revised 11/29/2000. University of New Mexico. [find](https://scholar.google.com/scholar?q=William+R%2E+Miller%2E+2000%2E+Motivational+Interviewing+Skill+Code+%28MISC%29+Coder%E2%80%99s+Manual%2E+Unpublished+manuscript%2E+Revised+11%2F29%2F2000%2E+University+of+New+Mexico%2E)
17. William R Miller, Theresa B Moyers, Denise Ernst, and Paul Amrhein. 2003. Manual for the motivational interviewing skill code (MISC). Unpublished manuscript. Albuquerque: Center on Alcoholism, Substance Abuse and Addictions, University of New Mexico. [find](https://scholar.google.com/scholar?q=William+R+Miller%2C+Theresa+B+Moyers%2C+Denise+Ernst%2C+and+Paul+Amrhein%2E+2003%2E+Manual+for+the+motivational+interviewing+skill+code+%28MISC%29%2E+Unpublished+manuscript%2E+Albuquerque%3A+Center+on+Alcoholism%2C+Substan)
18. William R Miller and Stephen Rollnick. 2013. Motivational Interviewing: Helping People Change, 3rd edition. Guilford Press. [find](https://scholar.google.com/scholar?q=William+R+Miller+and+Stephen+Rollnick%2E+2013%2E+Motivational+Interviewing%3A+Helping+People+Change%2C+3rd+edition%2E+Guilford+Press%2E)
19. Theresa B. Moyers, Lauren N. Rowell, Jennifer K Manuel, Denise B. Ernst, and Jon M. Houck. 2016. The motivational interviewing treatment integrity code (MITI 4): Rationale, preliminary reliability and validity. Journal of Substance Abuse Treatment, 65:36–42. [find](https://scholar.google.com/scholar?q=Theresa+B%2E+Moyers%2C+Lauren+N%2E+Rowell%2C+Jennifer+K+Manuel%2C+Denise+B%2E+Ernst%2C+and+Jon+M%2E+Houck%2E+2016%2E+The+motivational+interviewing+treatment+integrity+code+%28MITI+4%29%3A+Rationale%2C+preliminary+reliability+and)
20. William E. Narrow, Diana E. Clarke, S. Janet Kuramoto, Helena C. Kraemer, David J. Kupfer, Lisa Greiner, and Darrel A. Regier. 2013. DSM-5 field trials in the United States and Canada, Part III: Development and reliability testing of a cross-cutting symptom assessment for DSM-5. American Journal of… [find](https://scholar.google.com/scholar?q=William+E%2E+Narrow%2C+Diana+E%2E+Clarke%2C+S%2E+Janet+Kuramoto%2C+Helena+C%2E+Kraemer%2C+David+J%2E+Kupfer%2C+Lisa+Greiner%2C+and+Darrel+A%2E+Regier%2E+2013%2E+DSM%2D5+field+trials+in+the+United+States+and+Canada%2C+Part+III%3A+Devel)
21. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Tra… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
22. Mithat Can Ozgun, Jiahuan Pei, Koen Hindriks, Lucia Donatelli, Qingzhi Liu, and Junxiao Wang. 2025. Trustworthy AI psychotherapy: Multi-agent LLM workflow for counseling and explainable mental disorder diagnosis. In Proceedings of the 34th ACM International Conference on Information and Knowledge Ma… [find](https://scholar.google.com/scholar?q=Mithat+Can+Ozgun%2C+Jiahuan+Pei%2C+Koen+Hindriks%2C+Lucia+Donatelli%2C+Qingzhi+Liu%2C+and+Junxiao+Wang%2E+2025%2E+Trustworthy+AI+psychotherapy%3A+Multi%2Dagent+LLM+workflow+for+counseling+and+explainable+mental+disorde)
23. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22. Association for Comp… [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S%2E+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+3)
24. Verónica Pérez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, and Lawrence An. 2016. Building a motivational interviewing dataset. In Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pages 42–51. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ver%C3%B3nica+P%C3%A9rez%2DRosas%2C+Rada+Mihalcea%2C+Kenneth+Resnicow%2C+Satinder+Singh%2C+and+Lawrence+An%2E+2016%2E+Building+a+motivational+interviewing+dataset%2E+In+Proceedings+of+the+Third+Workshop+on+Computational+Lingui)
25. Huachuan Qiu and Zhenzhong Lan. 2024. [Interactive agents: Simulating counselor-client psychological counseling via role-playing LLM-to-LLM interactions](https://md.research.elamur.ai/free/en/papers/qiu-2026-interactive-agents-simulating-counselor-client/). Preprint, arXiv:2408.15787.
26. Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. [What makes a good conversation? How controllable attributes affect human judgments](https://md.research.elamur.ai/free/en/papers/see-2019-what-makes-good-conversation-how/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pag…
27. Ian Steenstra, Farnaz Nouraei, Mehdi Arjmand, and Timothy Bickmore. 2024. Virtual agents for alcohol use counseling: Exploring LLM-powered motivational interviewing. In Proceedings of the 24th ACM International Conference on Intelligent Virtual Agents, pages 1–10. Association for Computing Machinery… [find](https://scholar.google.com/scholar?q=Ian+Steenstra%2C+Farnaz+Nouraei%2C+Mehdi+Arjmand%2C+and+Timothy+Bickmore%2E+2024%2E+Virtual+agents+for+alcohol+use+counseling%3A+Exploring+LLM%2Dpowered+motivational+interviewing%2E+In+Proceedings+of+the+24th+ACM+Int)
28. Xin Sun, Jan de Wit, Zhuying Li, Jiahuan Pei, Abdallah El Ali, and Jos A. Bosch. 2025a. Script-strategy aligned generation: Aligning LLMs with expert-crafted dialogue scripts and therapeutic strategies for psychotherapy. Proceedings of the ACM on Human-Computer Interaction, 9(7). [find](https://scholar.google.com/scholar?q=Xin+Sun%2C+Jan+de+Wit%2C+Zhuying+Li%2C+Jiahuan+Pei%2C+Abdallah+El+Ali%2C+and+Jos+A%2E+Bosch%2E+2025a%2E+Script%2Dstrategy+aligned+generation%3A+Aligning+LLMs+with+expert%2Dcrafted+dialogue+scripts+and+therapeutic+strategie)
29. Xin Sun, Jiahuan Pei, Jan de Wit, Mohammad Aliannejadi, Emiel Krahmer, Jos T.P. Dobber, and Jos A. Bosch. 2024. Eliciting motivational interviewing skill codes in psychotherapy with LLMs: A bilingual dataset and analytical study. In Proceedings of the 2024 Joint International Conference on Computati… [find](https://scholar.google.com/scholar?q=Xin+Sun%2C+Jiahuan+Pei%2C+Jan+de+Wit%2C+Mohammad+Aliannejadi%2C+Emiel+Krahmer%2C+Jos+T%2EP%2E+Dobber%2C+and+Jos+A%2E+Bosch%2E+2024%2E+Eliciting+motivational+interviewing+skill+codes+in+psychotherapy+with+LLMs%3A+A+bilingual+)
30. Xin Sun, Xiao Tang, Abdallah El Ali, Zhuying Li, Pengjie Ren, Jan de Wit, Jiahuan Pei, and Jos A Bosch. 2025b. Rethinking the alignment of psychotherapy dialogue generation with motivational interviewing strategies. In Proceedings of the 31st International Conference on Computational Linguistics, pa… [find](https://scholar.google.com/scholar?q=Xin+Sun%2C+Xiao+Tang%2C+Abdallah+El+Ali%2C+Zhuying+Li%2C+Pengjie+Ren%2C+Jan+de+Wit%2C+Jiahuan+Pei%2C+and+Jos+A+Bosch%2E+2025b%2E+Rethinking+the+alignment+of+psychotherapy+dialogue+generation+with+motivational+interview)
31. Leili Tavabi, Trang Tran, Kalin Stefanov, Brian Borsari, Joshua Woolley, Stefan Scherer, and Mohammad Soleymani. 2021. Analysis of behavior classification in motivational interviewing. In Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, page… [find](https://scholar.google.com/scholar?q=Leili+Tavabi%2C+Trang+Tran%2C+Kalin+Stefanov%2C+Brian+Borsari%2C+Joshua+Woolley%2C+Stefan+Scherer%2C+and+Mohammad+Soleymani%2E+2021%2E+Analysis+of+behavior+classification+in+motivational+interviewing%2E+In+Proceedings+)
32. Tao Tu, Mike Schaekermann, Anil Palepu, and 1 others. 2025. Towards conversational diagnostic artificial intelligence. Nature, 642(8067):442–450. [find](https://scholar.google.com/scholar?q=Tao+Tu%2C+Mike+Schaekermann%2C+Anil+Palepu%2C+and+1+others%2E+2025%2E+Towards+conversational+diagnostic+artificial+intelligence%2E+Nature%2C+642%288067%29%3A442%E2%80%93450%2E)
33. Jiashuo Wang, Yang Xiao, Yanran Li, Changhe Song, Chunpu Xu, Chenhao Tan, and Wenjie Li. 2024a. Towards a client-centered assessment of LLM therapists by client simulation. Preprint, arXiv:2406.12266. — [arXiv:2406.12266](https://arxiv.org/abs/2406.12266) [find](https://scholar.google.com/scholar?q=Jiashuo+Wang%2C+Yang+Xiao%2C+Yanran+Li%2C+Changhe+Song%2C+Chunpu+Xu%2C+Chenhao+Tan%2C+and+Wenjie+Li%2E+2024a%2E+Towards+a+client%2Dcentered+assessment+of+LLM+therapists+by+client+simulation%2E+Preprint%2C+arXiv%3A2406%2E12266%2E)
34. Raj Sanjay Shah, Faye Holt, Shirley Anugrah Hayati, Aastha Agarwal, Yi-Chia Wang, Robert E Kraut, and Diyi Yang. 2022. Modeling motivational interviewing strategies on an online peer-to-peer counseling platform. Proceedings of the ACM on Human-Computer Interaction, 6(CSCW2):1–24. [find](https://scholar.google.com/scholar?q=Raj+Sanjay+Shah%2C+Faye+Holt%2C+Shirley+Anugrah+Hayati%2C+Aastha+Agarwal%2C+Yi%2DChia+Wang%2C+Robert+E+Kraut%2C+and+Diyi+Yang%2E+2022%2E+Modeling+motivational+interviewing+strategies+on+an+online+peer%2Dto%2Dpeer+counselin)
35. Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, and Hong Yu. 2024b. NoteChat: A dataset of synthetic patient-physician conversations conditioned on clinical notes. In Findings of the Association for Computational Linguistics, pages 15183–15201. Association for Co… [find](https://scholar.google.com/scholar?q=Junda+Wang%2C+Zonghai+Yao%2C+Zhichao+Yang%2C+Huixue+Zhou%2C+Rumeng+Li%2C+Xun+Wang%2C+Yucheng+Xu%2C+and+Hong+Yu%2E+2024b%2E+NoteChat%3A+A+dataset+of+synthetic+patient%2Dphysician+conversations+conditioned+on+clinical+notes%2E)
36. Ashish Sharma, Adam Miner, David Atkins, and Tim Althoff. 2020. [A computational approach to understanding empathy expressed in text-based mental health support](https://md.research.elamur.ai/free/en/papers/sharma-2020-computational-approach-understanding-empathy-expressed/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 5263–5276. Association for Computational L…
37. Ruiyi Wang, Stephanie Milani, Jamie C. Chiu, Jiayin Zhi, Shaun M. Eack, Travis Labrum, Samuel M Murphy, Nev Jones, Kate V Hardy, Hong Shen, Fei Fang, and Zhiyu Chen. 2024c. PATIENT-ψ: Using large language models to simulate patients for training mental health professionals. In Proceedings of the 202… [find](https://scholar.google.com/scholar?q=Ruiyi+Wang%2C+Stephanie+Milani%2C+Jamie+C%2E+Chiu%2C+Jiayin+Zhi%2C+Shaun+M%2E+Eack%2C+Travis+Labrum%2C+Samuel+M+Murphy%2C+Nev+Jones%2C+Kate+V+Hardy%2C+Hong+Shen%2C+Fei+Fang%2C+and+Zhiyu+Chen%2E+2024c%2E+PATIENT%2D%CF%88%3A+Using+large+lang)
38. Zixiu Wu, Simone Balloccu, Vivek Kumar, Rim Helaoui, Ehud Reiter, Diego Reforgiato Recupero, and Daniele Riboni. 2022. Anno-MI: A dataset of expert-annotated counselling dialogues. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 6177–6181. IEEE. [find](https://scholar.google.com/scholar?q=Zixiu+Wu%2C+Simone+Balloccu%2C+Vivek+Kumar%2C+Rim+Helaoui%2C+Ehud+Reiter%2C+Diego+Reforgiato+Recupero%2C+and+Daniele+Riboni%2E+2022%2E+Anno%2DMI%3A+A+dataset+of+expert%2Dannotated+counselling+dialogues%2E+In+ICASSP+2022%2D2022)
39. Zhouhang Xie, Bodhisattwa Prasad Majumder, Mengjie Zhao, Yoshinori Maeda, Keiichi Yamada, Hiromi Wakaki, and Julian McAuley. 2024. Few-shot dialogue strategy learning for motivational interviewing via inductive reasoning. In Findings of the Association for Computational Linguistics, pages 13207– 132… [find](https://scholar.google.com/scholar?q=Zhouhang+Xie%2C+Bodhisattwa+Prasad+Majumder%2C+Mengjie+Zhao%2C+Yoshinori+Maeda%2C+Keiichi+Yamada%2C+Hiromi+Wakaki%2C+and+Julian+McAuley%2E+2024%2E+Few%2Dshot+dialogue+strategy+learning+for+motivational+interviewing+via)
40. Howard Yen, Tianyu Gao, and Danqi Chen. 2024. [Long-context language modeling with parallel context encoding](https://md.research.elamur.ai/free/en/papers/yen-2024-long-context-language-modeling-parallel/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 2588–2610. Association for Computational Linguistics.
41. Congchi Yin, Feng Li, Shu Zhang, Zike Wang, Jun Shao, Piji Li, Jianhua Chen, and Xun Jiang. 2025. MDD-5k: A new diagnostic conversation dataset for mental disorders synthesized via neuro-symbolic LLM agents. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25715– 25… [find](https://scholar.google.com/scholar?q=Congchi+Yin%2C+Feng+Li%2C+Shu+Zhang%2C+Zike+Wang%2C+Jun+Shao%2C+Piji+Li%2C+Jianhua+Chen%2C+and+Xun+Jiang%2E+2025%2E+MDD%2D5k%3A+A+new+diagnostic+conversation+dataset+for+mental+disorders+synthesized+via+neuro%2Dsymbolic+LLM+)
42. Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, and Xiping Hu. 2024. CPsyCoun: A report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. In Findings of the Association for Computat… [find](https://scholar.google.com/scholar?q=Chenhao+Zhang%2C+Renhao+Li%2C+Minghuan+Tan%2C+Min+Yang%2C+Jingwei+Zhu%2C+Di+Yang%2C+Jiahao+Zhao%2C+Guancheng+Ye%2C+Chengming+Li%2C+and+Xiping+Hu%2E+2024%2E+CPsyCoun%3A+A+report%2Dbased+multi%2Dturn+dialogue+reconstruction+and+ev)
43. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. [Judging LLM-as-a-judge with MT-bench and Chatbot Arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). In Proceedings of the 37th International Conference on Neural Information Processing Systems,…
44. A Definition. Given a sequence of therapist MI codes c = (c 1 , . . . , c n ) where each c i ∈ C = {reflection, question, input, other}, we compute: H(c) = − X 1 p(c) log 2 p(c) log 2 \|C obs \| [find](https://scholar.google.com/scholar?q=A+Definition%2E+Given+a+sequence+of+therapist+MI+codes+c+%3D+%28c+1+%2C+%2E+%2E+%2E+%2C+c+n+%29+where+each+c+i+%E2%88%88+C+%3D+%7Breflection%2C+question%2C+input%2C+other%7D%2C+we+compute%3A+H%28c%29+%3D+%E2%88%92+X+1+p%28c%29+log+2+p%28c%29+log+2+%5C%7CC+obs+%5C%7C)

*Updated 31 October 2026*