Thai Humor Generation by Small Language Models

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Sirinaovakul B.; Muansuwan N.; Suwannahong K.; Limseelo C.; Chaithong S.; Poobanchuen P.

Publisher: Institute of Electrical and Electronics Engineers Inc.

Publication year: 2025

ISBN: 9798331522230

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-105014447264&doi=10.1109%2FECTI-CON64996.2025.11100466&partnerID=40&md5=45dac3290c1d81ba7b1504564fb4e8a4

Languages: English-Great Britain (EN-GB)

View on publisher site

Abstract

Despite the impressive capabilities of generative AI across multiple languages, generating humor that aligns with Thai cultural and linguistic nuances remains a significant challenge. Thai humor often relies on context, wordplay, and socio-cultural references, making it difficult for generic models to produce authentic jokes. This paper presents a focused approach to address this limitation by fine-tuning small language models (SLMs) on high-quality, non-synthetic Thai humor datasets. Llama-3.2-3B model was leveraged and Low-Rank Adaptation (LoRA) was employed for efficient parameter tuning, ensuring computational efficiency suitable for low-resource settings. Our work highlights humor as a critical benchmark for evaluating AI's understanding of language semantics and cultural context. A comprehensive evaluation was conducted with Thai participants to ensure the generated humor resonates with real-world cultural expectations. © 2025 Elsevier B.V., All rights reserved.

Keywords

No matching items found.