Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

30103 - Neurosciences (including psychophysiology)

Projekt

<a href="/cs/project/EH22_008%2F0004643" target="_blank" >EH22_008/0004643: Dynamika mozku</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW 2024

ISBN

979-8-3503-7451-3

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

351-355

Název nakladatele

IEEE

Místo vydání

New Jersey, USA

Místo konání akce

Soul, Korea

Datum konání akce

14. 4. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—