# Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy

arXiv: https://arxiv.org/abs/2411.06723 · HTML: https://mlsanity.com/paper/2411.06723/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 114 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [Expanding Explainability: Towards Social Transparency in AI systems](https://mlsanity.com/paper/2101.04719/) (2021)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation](https://mlsanity.com/paper/2203.13560/) (2022)
- [Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support](https://mlsanity.com/paper/2203.15144/) (2022)
- [Rasa: Open Source Language Understanding and Dialogue Management](https://mlsanity.com/paper/1712.05181/) (2017)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs](https://mlsanity.com/paper/2305.11792/) (2023)
- [Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations](https://mlsanity.com/paper/2305.10172/) (2023)
- [InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning](https://mlsanity.com/paper/2205.12673/) (2022)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation](https://mlsanity.com/paper/2112.07924/) (2021)
- [Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes](https://mlsanity.com/paper/1907.00326/) (2019)
- [Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform](https://mlsanity.com/paper/2211.05182/) (2022)
- [Transparent AI Disclosure Obligations: Who, What, When, Where, Why, How](https://mlsanity.com/paper/2403.06823/) (2024)
- [Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy](https://mlsanity.com/paper/2305.10195/) (2023)
- [A Survey of Natural Language Generation](https://mlsanity.com/paper/2112.11739/) (2021)
- [Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions](https://mlsanity.com/paper/2405.16402/) (2024)
- [Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies](https://mlsanity.com/paper/2408.06527/) (2024)
- [Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations](https://mlsanity.com/paper/2312.13871/) (2023)
- [CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation](https://mlsanity.com/paper/2305.06294/) (2023)

## Built on by (most cited first, 7 of 7)

- [Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis](https://mlsanity.com/paper/2508.11398/) (2025)
- [MultiJustice: A Chinese Dataset for Multi-Party, Multi-Charge Legal Prediction](https://mlsanity.com/paper/2507.06909/) (2025)
- [SafeTalkCoach: Diversity-Driven Multi-Agent Simulation for Parent-Teen Health Conversations](https://mlsanity.com/paper/2602.00017/) (2026)
- [Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers](https://mlsanity.com/paper/2604.20166/) (2026)
- [StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation](https://mlsanity.com/paper/2605.27393/) (2026)
- [CARE-MH: Towards Unified, Reproducible, and Comparable Evaluation of Mental Health LLMs](https://mlsanity.com/paper/2607.24754/) (2026)
- [ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls](https://mlsanity.com/paper/2608.11200/) (2026)

## Abstract (arXiv)

Chatbots or conversational agents (CAs) are increasingly used to improve access to digital psychotherapy. Many current systems rely on rigid, rule-based designs, heavily dependent on expert-crafted dialogue scripts for guiding therapeutic conversations. Although advances in large language models (LLMs) offer potential for more flexible interactions, their lack of controllability and explanability poses challenges in high-stakes contexts like psychotherapy. To address this, we conducted two studies in this work to explore how aligning LLMs with expert-crafted scripts can enhance psychotherapeutic chatbot performance. In Study 1 (N=43), an online experiment with a within-subjects design, we compared rule-based, pure LLM, and LLMs aligned with expert-crafted scripts via fine-tuning and prompting. Results showed that aligned LLMs significantly outperformed the other types of chatbots in empathy, dialogue relevance, and adherence to therapeutic principles. Building on findings, we proposed ``Script-Strategy Aligned Generation (SSAG)'', a more flexible alignment approach that reduces reliance on fully scripted content while maintaining LLMs' therapeutic adherence and controllability. In a 10-day field Study 2 (N=21), SSAG achieved comparable therapeutic effectiveness to full-scripted LLMs while requiring less than 40% of expert-crafted dialogue content. Beyond these results, this work advances LLM applications in psychotherapy by providing a controllable and scalable solution, reducing reliance on expert effort. By enabling domain experts to align LLMs through high-level strategies rather than full scripts, SSAG supports more efficient co-development and expands access to a broader context of psychotherapy.