3 papers
cs.CR2026
Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings
Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2
Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such a…
cs.CV2026
Transferable Low-Rank Convolutional Bases for Onboarding Unseen Medical Imaging Modalities
Ranat Das Prangon, Istiaque Ahmed, Shajid Hasan Naim +2
Deploying a medical imaging model that must later accommodate a modality it has never seen is a recurring practical problem: retraining the shared representation is expensive and d…
cs.CL2026
BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts
Kazi Noshin, Sajib Acharjee Dip, Ranat Das Prangon +4
Large language models (LLMs) increasingly participate in emotionally sensitive social conversations, where responses may shift from balanced support toward excessive validation or…