# The Thinking Therapist: Training Large Language Models to Deliver Acceptance and Commitment Therapy using Supervised Fine-Tuning and Odds Ratio Policy Optimization

arXiv: https://arxiv.org/abs/2509.09712 · HTML: https://mlsanity.com/paper/2509.09712/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 10 of 10)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering](https://mlsanity.com/paper/2403.16008/) (2024)
- [Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification](https://mlsanity.com/paper/2410.05318/) (2024)
- [LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing](https://mlsanity.com/paper/2502.02743/) (2025)
- [A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law](https://mlsanity.com/paper/2505.02665/) (2025)
- [Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an "AI Therapist"](https://mlsanity.com/paper/2412.15242/) (2024)
- [LLM-Powered Socially Assistive Robot-Delivered Cognitive Behavioral Therapy Exercises: an Exploratory Study with University Students](https://mlsanity.com/paper/2402.17937/) (2024)
- [Fine-Tuning Open-Weight Language Models to Deliver Cognitive Behavioral Therapy for Depression: A Feasibility Study](https://mlsanity.com/paper/2412.00251/) (2024)

## Built on by (most cited first, 2 of 2)

- [When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models](https://mlsanity.com/paper/2512.04124/) (2025)
- [Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars](https://mlsanity.com/paper/2606.17786/) (2026)

## Abstract (arXiv)

Acceptance and Commitment Therapy (ACT) is a third-wave cognitive behavioral therapy with emerging evidence of efficacy in several psychiatric conditions. This study investigates the impact of post-training methodology and explicit reasoning on the ability of a small open-weight large language model (LLM) to deliver ACT. Using synthetic ACT transcripts generated by Mistral-Large, we trained Llama-3.2-3b-Instruct with two distinct approaches, supervised fine-tuning (SFT) and odds ratio policy optimization (ORPO), each with and without an explicit chain-of-thought (COT) reasoning step. Performance was evaluated by comparing these four post-trained variants against the base Instruct model. These models were benchmarked in simulated therapy sessions, with performance quantitatively assessed on the ACT Fidelity Measure (ACT-FM) and the Therapist Empathy Scale (TES) by an LLM judge that had been fine-tuned on human evaluations. Our findings demonstrate that the ORPO-trained models significantly outperformed both their SFT and Instruct counterparts on ACT fidelity (chi2(5) = 185.15, p < .001) and therapeutic empathy (chi2(5) = 140.37, p < .001). The effect of COT was conditional as it provided a significant benefit to SFT models, improving ACT-FM scores by an average of 2.68 points (p < .001), while offering no discernible advantage to the superior ORPO or instruct-tuned variants. We posit that the superiority of ORPO stems from its ability to learn the therapeutic `process' over imitating `content,' a key aspect of ACT, while COT acts as a necessary scaffold for models trained only via imitation. This study establishes that preference-aligned policy optimization can effectively instill ACT competencies in small LLMs, and that the utility of explicit reasoning is highly dependent on the underlying training paradigm.