---
title: "From Responses to Trajectories: Modeling the Development of"
description: "Reflective listening is a central skill in motivational interviewing (MI). 13 references. Among them: 0."
authors: ["Dhruvil Thummar", "Verónica Pérez-Rosas"]
year: 2026
venue: "Proceedings of the 11th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)"
source: "https://aclanthology.org/2026.clpsych-1.18/"
doi: "10.18653/v1/2026.clpsych-1.18"
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/thummar-2026-responses-trajectories-modeling-development-reflective/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/thummar-2026-responses-trajectories-modeling-development-reflective/)

[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/31/) / From Responses to Trajectories: Modeling the Development of Reflective Listening Skills

# From Responses to Trajectories: Modeling the Development of Reflective Listening Skills

**Authors:** Dhruvil Thummar and [Verónica Pérez-Rosas](https://md.research.elamur.ai/free/en/authors/veronica-perez-rosas/) · **Year:** 2026 · **Venue:** [Proceedings of the 11th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)](https://md.research.elamur.ai/free/en/venues/clpsych/) ([Workshop on Computational Linguistics and Clinical Psychology 2026](https://md.research.elamur.ai/free/en/venues/clpsych/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.clpsych-1.18/) · [PDF](https://aclanthology.org/2026.clpsych-1.18.pdf) · [DOI 10.18653/v1/2026.clpsych-1.18](https://doi.org/10.18653/v1/2026.clpsych-1.18) · [OpenAlex](https://openalex.org/W7166863733)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Reflective listening is a central skill in motivational interviewing (MI). It is hard to teach at scale because expert supervision is scarce, and earlier NLP tools mostly score single responses rather than following a learner over time. This paper treats skill practice as a trajectory instead. The authors reuse data from the PAIR user study (Min et al., 2022), collected in a graduate MI course with three weekly assignments. They keep 6,196 responses from 68 students who took part in all three weeks. Each response is encoded with BGE-M3, and the prompt's embedding is subtracted to remove shared content. The resulting residual vectors are averaged per student and week, then compared across weeks with cosine, Euclidean and Manhattan measures. Later weeks are closer together and less variable, which suggests trainees' language is stabilizing. Responses to different prompts within a week stay diverse, so trainees are not falling back on templates. LIWC features change only slightly. The approach points toward feedback systems that track learner progress, though it does not measure clinical competence directly.

## Key points
- **Data:** The full PAIR study set has 7,264 prompt–response pairs from 90 students. The longitudinal subset uses 68 consistent participants and 6,196 responses, and Texas State University's IRB judged this use exempt.
- **Method:** Each residual is the response embedding minus the prompt embedding (BGE-M3, L2-normalized). This assumes embeddings combine roughly linearly.
- **Cross-week similarity:** Mean cosine was 0.74 for W1–W2, 0.77 for W2–W3 and 0.68 for W1–W3. Euclidean distance went 0.25 → 0.23 → 0.27 and Manhattan distance 6.21 → 5.74 → 6.80 over the same intervals.
- **Within-week similarity:** It stayed low, with means from 0.146 to 0.166. Upper- and lower-quartile students were used as examples of consistent and variable trajectories.
- **LIWC trends:** Markers of directive framing declined from Week 1 to Week 3, with auxiliary verbs falling from 11.36 to 10.39 and certainty from 1.10 to 0.80. Second-person "you" stayed roughly constant at about 13.8–14.5.

*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

- [Texas State University](https://md.research.elamur.ai/free/en/universities/texas-state-university/) — University, San Marcos, United States · 3 works · 190 citations

📚 Shelves (4): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 306 works

## Cite

Cite as: Dhruvil Thummar and Verónica Pérez-Rosas. 2026. From Responses to Trajectories: Modeling the Development of Reflective Listening Skills. Proceedings of the 11th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026).

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

```bibtex
@inproceedings{thummar2026responses,
  title = {{From Responses to Trajectories: Modeling the Development of Reflective Listening Skills}},
  author = {Dhruvil Thummar and Verónica Pérez-Rosas},
  booktitle = {Proceedings of the 11th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.clpsych-1.18},
  url = {https://doi.org/10.18653/v1/2026.clpsych-1.18}
}
```

- [← previous From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding](https://md.research.elamur.ai/free/en/papers/wang-2026-recognition-reasoning-benchmarking-enhancing-mllms/)
- [next → From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks](https://md.research.elamur.ai/free/en/papers/majmudar-2026-rosetta-match-up-paired-corpus/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/)

## References

13 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Victor Ardulov, Victor R. Martinez, Krishna Somandepalli, Allison Lahnala, Jill Burstein, and Shrikanth Narayanan. 2022. Local dynamic mode decomposition for assessing therapist competency in cognitive behavioral therapy sessions. In Proceedings of the 23rd Annual Conference of the International Spe… [find](https://scholar.google.com/scholar?q=Victor+Ardulov%2C+Victor+R%2E+Martinez%2C+Krishna+Somandepalli%2C+Allison+Lahnala%2C+Jill+Burstein%2C+and+Shrikanth+Narayanan%2E+2022%2E+Local+dynamic+mode+decomposition+for+assessing+therapist+competency+in+cognitiv)
2. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. [BGE M3-Embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). arXiv preprint arXiv:2402.03216.
3. Nikolaos Flemotomos, Victor R. Martinez, Zhuohao Chen, Torrey A. Creed, David C. Atkins, and Shrikanth Narayanan. 2021. Automated quality assessment of cognitive behavioral therapy sessions through highly contextualized language representations. PLOS ONE, 16(10):e0258639. [find](https://scholar.google.com/scholar?q=Nikolaos+Flemotomos%2C+Victor+R%2E+Martinez%2C+Zhuohao+Chen%2C+Torrey+A%2E+Creed%2C+David+C%2E+Atkins%2C+and+Shrikanth+Narayanan%2E+2021%2E+Automated+quality+assessment+of+cognitive+behavioral+therapy+sessions+through+hi)
4. William R Miller and Stephen Rollnick. 2012. Motivational interviewing: Helping people change. Guilford press. [find](https://scholar.google.com/scholar?q=William+R+Miller+and+Stephen+Rollnick%2E+2012%2E+Motivational+interviewing%3A+Helping+people+change%2E+Guilford+press%2E)
5. Do June Min, Veronica Perez-Rosas, Ken Resnicow, and Rada Mihalcea. 2023. VERVE: Template-based ReflectiVE rewriting for MotiVational IntErviewing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10289–10302, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Do+June+Min%2C+Veronica+Perez%2DRosas%2C+Ken+Resnicow%2C+and+Rada+Mihalcea%2E+2023%2E+VERVE%3A+Template%2Dbased+ReflectiVE+rewriting+for+MotiVational+IntErviewing%2E+In+Findings+of+the+Association+for+Computational+Lin)
6. Do June Min, Verónica Pérez-Rosas, Kenneth Resnicow, and Rada Mihalcea. 2022. PAIR: Prompt-aware margIn ranking for counselor reflection scoring in motivational interviewing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 148–158, Abu Dhabi, United A… [find](https://scholar.google.com/scholar?q=Do+June+Min%2C+Ver%C3%B3nica+P%C3%A9rez%2DRosas%2C+Kenneth+Resnicow%2C+and+Rada+Mihalcea%2E+2022%2E+PAIR%3A+Prompt%2Daware+margIn+ranking+for+counselor+reflection+scoring+in+motivational+interviewing%2E+In+Proceedings+of+the+202)
7. Theresa B Moyers, Tim Martin, Jon M Houck, Paulette J Christopher, and J Scott Tonigan. 2009. From in-session behaviors to drinking outcomes: a causal chain for motivational interviewing. Journal of consulting and clinical psychology, 77(6):1113. [find](https://scholar.google.com/scholar?q=Theresa+B+Moyers%2C+Tim+Martin%2C+Jon+M+Houck%2C+Paulette+J+Christopher%2C+and+J+Scott+Tonigan%2E+2009%2E+From+in%2Dsession+behaviors+to+drinking+outcomes%3A+a+causal+chain+for+motivational+interviewing%2E+Journal+of+c)
8. Theresa B Moyers, Lauren N Rowell, Jennifer K Manuel, Denise 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+Moyers%2C+Lauren+N+Rowell%2C+Jennifer+K+Manuel%2C+Denise+Ernst%2C+and+Jon+M+Houck%2E+2016%2E+The+motivational+interviewing+treatment+integrity+code+%28miti+4%29%3A+rationale%2C+preliminary+reliability+and+valid)
9. Verónica Pérez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, and Lawrence An. 2017a. Understanding and predicting empathic behavior in counseling therapy. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1426– 1435, V… [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+2017a%2E+Understanding+and+predicting+empathic+behavior+in+counseling+therapy%2E+In+Proceedings+of+the+55th+Annual+M)
10. Verónica Pérez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, Lawrence An, Kathy J. Goggin, and Delwyn Catley. 2017b. Predicting counselor behaviors in motivational interviewing encounters. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Li… [find](https://scholar.google.com/scholar?q=Ver%C3%B3nica+P%C3%A9rez%2DRosas%2C+Rada+Mihalcea%2C+Kenneth+Resnicow%2C+Satinder+Singh%2C+Lawrence+An%2C+Kathy+J%2E+Goggin%2C+and+Delwyn+Catley%2E+2017b%2E+Predicting+counselor+behaviors+in+motivational+interviewing+encounters%2E+I)
11. Verónica Pérez-Rosas, Xinyi Wu, Kenneth Resnicow, and Rada Mihalcea. 2019. What makes a good counselor? learning to distinguish between high-quality and low-quality counseling conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 926–935, Fl… [find](https://scholar.google.com/scholar?q=Ver%C3%B3nica+P%C3%A9rez%2DRosas%2C+Xinyi+Wu%2C+Kenneth+Resnicow%2C+and+Rada+Mihalcea%2E+2019%2E+What+makes+a+good+counselor%3F+learning+to+distinguish+between+high%2Dquality+and+low%2Dquality+counseling+conversations%2E+In+Procee)
12. Siqi Shen, Veronica Perez-Rosas, Charles Welch, Soujanya Poria, and Rada Mihalcea. 2022. Knowledge enhanced reflection generation for counseling dialogues. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3096–3107, Dublin, Ire… [find](https://scholar.google.com/scholar?q=Siqi+Shen%2C+Veronica+Perez%2DRosas%2C+Charles+Welch%2C+Soujanya+Poria%2C+and+Rada+Mihalcea%2E+2022%2E+Knowledge+enhanced+reflection+generation+for+counseling+dialogues%2E+In+Proceedings+of+the+60th+Annual+Meeting+of)
13. Yla R Tausczik and James W Pennebaker. 2010. The psychological meaning of words: Liwc and computerized text analysis methods. Journal of language and social psychology, 29(1):24–54. [find](https://scholar.google.com/scholar?q=Yla+R+Tausczik+and+James+W+Pennebaker%2E+2010%2E+The+psychological+meaning+of+words%3A+Liwc+and+computerized+text+analysis+methods%2E+Journal+of+language+and+social+psychology%2C+29%281%29%3A24%E2%80%9354%2E)

*Updated 1 November 2026*