Exploring Bengali Creative Storytelling Capabilities of Large Language Models Across Cultural Variations

  • Wasi, Azmine Toushik
  • Islam, Raima
  • Islam, Mst Rafia
  • Sadeque, Farig Y.
  • Rafi, Taki Hasan
  • ... Chae, Dong-Kyu
Citations

SCOPUS

1

초록

Large Language Models (LLMs) excel in fluency but often struggle with originality, suspense, and emotional depth in storytelling. This study evaluates their creative storytelling capabilities in Bengali, a language with significant dialectal diversity. Using three narrative prompts across single-dialect and cross-dialect settings with initial results and story continuation, we analyze AI-generated content for coherence, creativity, and cultural relevance. Native Bengali speakers provide qualitative feedback, highlighting key challenges such as dialectal fidelity and narrative richness. Our findings emphasize the need for culturally adaptive NLP models to enhance storytelling in low-resource languages.

키워드

Bengali languageCultural biasDialectal biasFairnessHuman-centered NLPinclusionLarge language modelsLLM auditingComputational linguistics
제목
Exploring Bengali Creative Storytelling Capabilities of Large Language Models Across Cultural Variations
저자
Wasi, Azmine ToushikIslam, RaimaIslam, Mst RafiaSadeque, Farig Y.Rafi, Taki HasanChae, Dong-Kyu
DOI
10.1145/3715070.3749228
발행일
2025-10
유형
Conference paper
저널명
Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW
페이지
214 ~ 218