BengaliFig puts AI to the test on Bengali riddles
Can your favorite AI solve a Bengali riddle? BengaliFig is a new challenge set that puts large language models to the test on figurative, culturally grounded reasoning in Bengali—a widely spoken but low-resourced language.
The dataset packs 435 riddles from oral and literary traditions, each richly labeled across five axes: reasoning type, trap type, cultural depth, answer category, and difficulty. Items are turned into multiple-choice questions via a constraint-aware, AI-assisted pipeline.
In evaluations of eight leading LLMs with zero-shot and few-shot chain-of-thought prompts, models consistently struggled with metaphorical clues and culture-specific knowledge—revealing blind spots hidden by broad multilingual benchmarks.
- A compact, diagnostic probe for robustness in low-resource settings
- A step toward inclusive, heritage-aware NLP evaluation
By centering riddles that millions grew up with, BengaliFig asks AI to meet people where they are.
Paper by Abdullah Al Sefat. Read: https://arxiv.org/abs/2511.20399v1
Paper: https://arxiv.org/abs/2511.20399v1
Register: https://www.AiFeta.com
#Bengali #NLP #LLM #CulturalAI #LowResource #Evaluation
