Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
- URL: http://arxiv.org/abs/2404.16160v1
- Date: Wed, 24 Apr 2024 19:30:18 GMT
- Title: Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
- Authors: Cheng Kang, Daniel Novak, Katerina Urbanova, Yuqing Cheng, Yong Hu,
- Abstract summary: We propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy.
We observe that pre-trained LLMs on Psychotherapy Assistant Instructions outperform state-of-the-art LLMs response baselines.
- Score: 1.5706140100056272
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data. However, the limited quantity, diversity, and professional expertise of such instruction data raise concerns about the performance of LLMs in psychotherapy tasks when provided with domain-specific instructions. To address this, we firstly propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy, and secondly, we use an adaption fine-tuning method and retrieval augmented generation method to improve pre-trained LLMs. Through quantitative evaluation of linguistic quality using automatic and human evaluation, we observe that pre-trained LLMs on Psychotherapy Assistant Instructions outperform state-of-the-art LLMs response baselines. Our Assistant-Instruction approach offers a half-annotation method to align pre-trained LLMs with instructions and provide pre-trained LLMs with more psychotherapy knowledge.
Related papers
- Optimizing Psychological Counseling with Instruction-Tuned Large Language Models [9.19192059750618]
This paper explores the application of large language models (LLMs) in psychological counseling.
We present a method for instruction tuning LLMs with specialized prompts to enhance their performance in providing empathetic, relevant, and supportive responses.
arXiv Detail & Related papers (2024-06-19T15:13:07Z) - A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations [5.265452667976959]
Large Language Models (LLMs) have demonstrated surprising performance across various natural language processing tasks.
This survey systematically explores how to train medical LLMs based on general LLMs.
arXiv Detail & Related papers (2024-06-14T02:42:20Z) - Developing Healthcare Language Model Embedding Spaces [0.20971479389679337]
Pre-trained Large Language Models (LLMs) often struggle on out-of-domain datasets like healthcare focused text.
Three methods are assessed: traditional masked language modeling, Deep Contrastive Learning for Unsupervised Textual Representations (DeCLUTR) and a novel pre-training objective utilizing metadata categories from the healthcare settings.
Contrastively trained models outperform other approaches on the classification tasks, delivering strong performance from limited labeled data and with fewer model parameter updates required.
arXiv Detail & Related papers (2024-03-28T19:31:32Z) - ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences [51.66185471742271]
We propose ChiMed-GPT, a benchmark LLM designed explicitly for Chinese medical domain.
ChiMed-GPT undergoes a comprehensive training regime with pre-training, SFT, and RLHF.
We analyze possible biases through prompting ChiMed-GPT to perform attitude scales regarding discrimination of patients.
arXiv Detail & Related papers (2023-11-10T12:25:32Z) - Auto-Instruct: Automatic Instruction Generation and Ranking for
Black-Box Language Models [91.02730155418699]
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions.
We introduce Auto-Instruct, a novel method to automatically improve the quality of instructions provided to LLMs.
In experiments on 118 out-of-domain tasks, Auto-Instruct surpasses both human-written instructions and existing baselines of LLM-generated instructions.
arXiv Detail & Related papers (2023-10-19T19:52:55Z) - Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
Low-quality data in the training set are usually detrimental to instruction tuning.
We propose a novel method, termed "reflection-tuning"
This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
arXiv Detail & Related papers (2023-10-18T05:13:47Z) - Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models [79.32652077838046]
We introduce Parrot, a solution aiming to enhance multi-turn instruction following for large language models (LLMs)
First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis.
Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction.
arXiv Detail & Related papers (2023-10-11T08:36:43Z) - SELF: Self-Evolution with Language Feedback [68.6673019284853]
'SELF' (Self-Evolution with Language Feedback) is a novel approach to advance large language models.
It enables LLMs to self-improve through self-reflection, akin to human learning processes.
Our experiments in mathematics and general tasks demonstrate that SELF can enhance the capabilities of LLMs without human intervention.
arXiv Detail & Related papers (2023-10-01T00:52:24Z) - Aligning Large Language Models for Clinical Tasks [0.0]
Large Language Models (LLMs) have demonstrated remarkable adaptability, showcasing their capacity to excel in tasks for which they were not explicitly trained.
We propose an alignment strategy for medical question-answering, known as 'expand-guess-refine'
A preliminary analysis of this method demonstrated outstanding performance, achieving a score of 70.63% on a subset of questions sourced from the USMLE dataset.
arXiv Detail & Related papers (2023-09-06T10:20:06Z) - Aligning Large Language Models with Human: A Survey [53.6014921995006]
Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks.
Despite their notable performance, these models are prone to certain limitations such as misunderstanding human instructions, generating potentially biased content, or factually incorrect information.
This survey presents a comprehensive overview of these alignment technologies, including the following aspects.
arXiv Detail & Related papers (2023-07-24T17:44:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.