Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech
Paper • 2608.02941 • Published
Adib Sakhawat
sakhadib
AI & ML interests
Low-resource NLP (Bangla), LLM evaluation & benchmarks, AI safety, multilingual embeddings. Affiliate Researcher, Systems and Software Lab, IUT.
Recent Activity
authored a paper about 5 hours ago
Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech authored a paper about 5 hours ago
Hubness, Not Anisotropy, Drives Cross-Lingual Retrieval Asymmetry in Multilingual Embedding ModelsOrganizations
None yet
authored 7
papers about 5 hours ago
Hubness, Not Anisotropy, Drives Cross-Lingual Retrieval Asymmetry in Multilingual Embedding Models
Paper • 2605.26575 • Published
Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives
Paper • 2610.17402 • Published
Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure
Paper • 2609.29445 • Published
AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models
Paper • 2602.16639 • Published
AIDG: A Formal Decomposition of Information Extraction and Containment Asymmetries in Multi-Turn LLM Dialogue
Paper • 2602.17443 • Published
BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025)
Paper • 2607.17111 • Published
updated 2
datasets about 8 hours ago
authored 4
papers 1 day ago
When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms
Paper • 2602.12921 • Published
Literal Lock-In: How Test Language Shifts Literal Attraction in Typed Decision Models on Bengali Idioms
Paper • 2610.22526 • Published
LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution
Paper • 2606.28335 • Published
Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
Paper • 2601.06194 • Published
liked a
dataset 1 day ago
published a
dataset 1 day ago
updated a
dataset 9 months ago
published a
dataset 9 months ago
published a
dataset over 1 year ago