Ajou University repository

PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models
  • Han, Ji Eun ;
  • Koh, Jun Seok ;
  • Seo, Hyeon Tae ;
  • Chang, Du Seong ;
  • Sohn, Kyung Ah
Citations

SCOPUS

0

Citation Export

DC Field Value Language
dc.contributor.authorHan, Ji Eun-
dc.contributor.authorKoh, Jun Seok-
dc.contributor.authorSeo, Hyeon Tae-
dc.contributor.authorChang, Du Seong-
dc.contributor.authorSohn, Kyung Ah-
dc.date.issued2024-01-01-
dc.identifier.urihttps://aurora.ajou.ac.kr/handle/2018.oak/37105-
dc.identifier.urihttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85195944438&origin=inward-
dc.description.abstractWe present a novel end-to-end personality-based synthetic dialogue data generation pipeline, specifically designed to elicit responses from large language models via prompting. We design the prompts to generate more human-like dialogues considering real-world scenarios when users engage with chatbots. We introduce PSYDIAL, the first Korean dialogue dataset focused on personality-based dialogues, curated using our proposed pipeline. Notably, we focus on the Extraversion dimension of the Big Five personality model in our research. Experimental results indicate that while pre-trained models and those fine-tuned with a chit-chat dataset struggle to generate responses reflecting personality, models trained with PSYDIAL show significant improvements. The versatility of our pipeline extends beyond dialogue tasks, offering potential for other non-dialogue related applications. This research opens doors for more nuanced, personality-driven conversational AI in Korean and potentially other languages. Our code is publicly available at https://github.com/jiSilverH/psydial.-
dc.description.sponsorshipThis work was supported by the National Research Foundation of Korea(NRF) grant (No. NRF2022R1A2C1007434) and by the Institute of Information and Communications Technology Planning and Evaluation (IITP) under Grant 2021-0-02068 (Artificial Intelligence Innovation Hub) and under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2023-RS-2023-00255968) grant, funded by the Korea government(MSIT). This work was also supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (RS-2022-00143911,AI Excellence Global Innovative Leader Education Program).-
dc.language.isoeng-
dc.publisherEuropean Language Resources Association (ELRA)-
dc.subject.meshData generation-
dc.subject.meshDialogue generations-
dc.subject.meshEnd to end-
dc.subject.meshHuman like-
dc.subject.meshLanguage model-
dc.subject.meshLarge language model-
dc.subject.meshPersonality modeling-
dc.subject.meshPersonality-based dialog-
dc.subject.meshReal-world scenario-
dc.subject.meshSynthetic dialog generation-
dc.titlePSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models-
dc.typeConference-
dc.citation.conferenceDate2024.5.20. ~ 2024.5.25.-
dc.citation.conferenceNameJoint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024-
dc.citation.edition2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings-
dc.citation.endPage13331-
dc.citation.startPage13321-
dc.citation.title2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings-
dc.identifier.bibliographicCitation2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings, pp.13321-13331-
dc.identifier.scopusid2-s2.0-85195944438-
dc.subject.keywordlarge language model-
dc.subject.keywordpersonality-based dialogue-
dc.subject.keywordsynthetic dialogue generation-
dc.type.otherConference Paper-
dc.subject.subareaTheoretical Computer Science-
dc.subject.subareaComputational Theory and Mathematics-
dc.subject.subareaComputer Science Applications-
Show simple item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.