Usman Naseem

Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings

2024 · arXiv (Cornell University)

Large language models (LLMs) have garnered significant interest in natural language processing (NLP), particularly their remarkable performance in various downstream tasks in resource-rich languages. Recent studies have highlighted the limitations of LLMs in low-resource languages, …

XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content

2026

Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence.However, existing safety evaluations often rely on simplistic binary labels (safe/unsafe), overlooking the nuanced spectrum of risk these outputs pose.To address …

Alleviating Textual Reliance in Medical Language-Guided Segmentation via Prototype-Driven Semantic Approximation

2025

Medical language-guided segmentation, integrating textual clinical reports as auxiliary guidance to enhance image segmentation, has demonstrated significant improvements over unimodal approaches. However, its inherent reliance on paired image-text input, which we refer to as ``textual …

Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities

2025 · arXiv (Cornell University)

Recent advancements in large language models (LLMs) have transformed natural language understanding and generation, leading to extensive benchmarking across diverse tasks. However, cryptanalysis - a critical area for data security and its connection to LLMs' …

Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning

2026

Internet memes are powerful tools for communication, capable of spreading political, psychological, and sociocultural ideas. However, they can be harmful and can be used to disseminate hate toward targeted individuals or groups. Although previous studies …