# Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model

arXiv: https://arxiv.org/abs/2402.01051 · HTML: https://mlsanity.com/paper/2402.01051/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://mlsanity.com/paper/1903.12136/) (2019)
- [Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR](https://mlsanity.com/paper/2210.05793/) (2022)

## Built on by (most cited first, 5 of 5)

- [Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data](https://mlsanity.com/paper/2410.18588/) (2024)
- [A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions](https://mlsanity.com/paper/2502.11095/) (2025)
- [TempoFormer: A Transformer for Temporally-aware Representations in Change Detection](https://mlsanity.com/paper/2408.15689/) (2024)
- [A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit](https://mlsanity.com/paper/2505.17362/) (2025)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)

## Abstract (arXiv)

Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific capabilities of foundational models into smaller models that can be owned and controlled. In the development of a therapeutic chatbot, we wish to distill a capability known as reflective listening, in which a therapist produces reflections of client speech. These reflections either restate what a client has said, or connect what was said to a relevant observation, idea or guess that encourages and guides the client to continue contemplation. In this paper, we present a method for distilling the generation of reflections from a Foundational Language Model (GPT-4) into smaller models. We first show that GPT-4, using zero-shot prompting, can generate reflections at near 100% success rate, superior to all previous methods. Using reflections generated by GPT-4, we fine-tune different sizes of the GPT-2 family. The GPT-2-small model achieves 83% success on a hold-out test set and the GPT-2 XL achieves 90% success. We also show that GPT-4 can help in the labor-intensive task of evaluating the quality of the distilled models, using it as a zero-shot classifier. Using triple-human review as a guide, the classifier achieves a Cohen-Kappa of 0.66, a substantial inter-rater reliability figure.