Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00023752%3A_____%2F24%3A43921396" target="_blank" >RIV/00023752:_____/24:43921396 - isvavai.cz</a>
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
<a href="http://dx.doi.org/10.1109/ICASSPW62465.2024.10626529" target="_blank" >10.1109/ICASSPW62465.2024.10626529</a>
Alternative languages
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
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
30103 - Neurosciences (including psychophysiology)
Result continuities
Project
<a href="/en/project/EH22_008%2F0004643" target="_blank" >EH22_008/0004643: Brain dynamics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024
ISBN
979-8-3503-7451-3
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
351-355
Publisher name
IEEE
Place of publication
New Jersey, USA
Event location
Soul, Korea
Event date
Apr 14, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—