BengaliFig puts AI to the test on Bengali riddles

Kari Jaaskelainen

26 Nov 2025 — 1 min read

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

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A