paper-with-me

Papers

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

2024-11-11 · Xin Sun, Jan de Wit, Zhuying Li, Jiahuan Pei, Abdallah El Ali, Jos A. Bosch

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 recent advances in large language models (LLMs) offer the potential for more flexible interactions, their lack of controllability and transparency poses significant challenges in sensitive areas like psychotherapy. In this work, we explored how aligning LLMs with expert-crafted scripts can enhance psychotherapeutic chatbot performance. Our comparative study showed that LLMs aligned with expert-crafted scripts through prompting and fine-tuning significantly outperformed both pure LLMs and rule-based chatbots, achieving a more effective balance between dialogue flexibility and adherence to therapeutic principles. Building on findings, we proposed ``Script-Strategy Aligned Generation (SSAG)'', a flexible alignment approach that reduces reliance on fully scripted content while enhancing LLMs' therapeutic adherence and controllability. In a 10-day field study, SSAG demonstrated performance comparable to full script alignment and outperformed rule-based chatbots, empirically supporting SSAG as an efficient approach for aligning LLMs with domain expertise. Our work advances LLM applications in psychotherapy by providing a controllable, adaptable, and scalable solution for digital interventions, reducing reliance on expert effort. It also provides a collaborative framework for domain experts and developers to efficiently build expertise-aligned chatbots, broadening access to psychotherapy and behavioral interventions.

📄 PDF Abstract BibTeX arXiv:2411.06723

Code (0)

등록된 구현이 없습니다.

Tasks

Chatbot

Similar Papers 제목 키워드 기반

Grammar and Gameplay-aligned RL for Game Description Generation with LLMs

2025-03-20 · Tsunehiko Tanaka, Edgar Simo-Serra

Game Description Generation (GDG) is the task of generating a game description written in a Game Description Language (GDL) from natural language text. Previous studies have explored generation methods leveraging the con…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Aligning LLMs by Predicting Preferences from User Writing Samples

2025-05-27 · Stéphane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald, Katherine Metcalf

Accommodating human preferences is essential for creating aligned LLM agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs acting as writing agents to infer a descript…

Weak-to-Strong Jailbreaking on Large Language Models

2024-01-30 · Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du 외

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose…

Aligning Teacher with Student Preferences for Tailored Training Data Generation

2024-06-27 · Yantao Liu, Zhao Zhang, Zijun Yao, Shulin Cao 외

Large Language Models (LLMs) have shown significant promise as copilots in various tasks. Local deployment of LLMs on edge devices is necessary when handling privacy-sensitive data or latency-sensitive tasks. The computa…

In-Context LearningKnowledge Distillation

LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model

2024-05-06 · Haowen Sun, Ruikun Zheng, Haibin Huang, Chongyang Ma 외

In this paper, we introduce LGTM, a novel Local-to-Global pipeline for Text-to-Motion generation. LGTM utilizes a diffusion-based architecture and aims to address the challenge of accurately translating textual descripti…

Motion Generation