14 papers
Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering
Noor Islam S. Mohammad, UluÄ Bayazıt
Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external…
Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
Noor Islam S. Mohammad, UluÄ Bayazıt
We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce \textbf{Attribution Graphs} (AGs), which extend GradCAM++ to circuit-level…
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
Noor Islam S. Mohammad, Ulug Bayazit
Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no m…
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
Noor Islam S. Mohammad, Mahmudul Hasan
Large language models (LLMs) deployed for logical reasoning in knowledge-intensive domains exhibit a subtle but critical failure: coherence can be vacuously achieved through system…
MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions
Noor Islam S. Mohammad, Tamim Sheikh
Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer…
The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
Noor Islam S. Mohammad, Tamim Sheikh
Autoformalization, translating natural-language mathematics into formal proof assistants, is bottlenecked not by translation fluency but by \emph{faithfulness}: a formal statement…