Automatic Generation and Detection of Motivational Interviewing-style Reflections for Smoking Cessation Therapeutic Conversations using Transformer-based Language Models
Bibliographic record
Abstract
If conversational agents can take on a therapeutic role, they may provide a scalable way to help many more people suffering from addictions. Motivational Interviewing (MI) is a validated therapy for behaviour change that has been used to help smokers to quit. A key MI skill is to produce reflections on a patient’s statements about a behaviour. Reflections are simple restatements or complex inferences drawing on conversation history or general experience. This thesis presents a method of generating reflections using GPT-2 and GPT-3 language models. These models produce promising reflections; however, some generated reflections are poor quality. To address this, we train a classifier on samples labeled by an MI expert to act as a filter. Its sensitivity is 90%, and specificity 71%. GPT-2 produces reflections 54% of the time with few-shot priming which GPT-3 improves to 89%. With fine-tuning and filtering, GPT-2 generation hit-rate improves to 81%.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".