Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00377571" target="_blank" >RIV/68407700:21230/24:00377571 - isvavai.cz</a>

Alternative codes found

RIV/68407700:21730/24:00377571

Result on the web

<a href="https://ieeexplore.ieee.org/document/10626529" target="_blank" >https://ieeexplore.ieee.org/document/10626529</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

Original language description

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 more psychotherapy knowledge.

Czech name

—

Czech description

—

Type

W - Workshop organization

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Event location

Seoul

Event country

KR - KOREA, REPUBLIC OF

Event starting date

—

Event ending date

—

Total number of attendees

4400

Foreign attendee count

—

Type of event by attendee nationality

CST - Celostátní akce