8 papers
Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies
Sung Ju Lee, Nam Ik Cho
Watermarking diffusion-generated images requires balancing provenance signals with image quality, robustness, and computational cost. This work organizes methods along two axes: in…
Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration
Mohamad Zbib, Ammar Mohanna
Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade-off. We evaluate it using ben…
Toward Trustworthy Large Language Model Agents in Healthcare
Hadi Hasan, Safaa Salman, Adam Tai Abou Dargham +2
Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordination, fragmented legacy systems, and high administrative overhead. These ine…
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
Ali Slim, Haydar Hamieh, Jawad Kotaich +5
Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks, making it difficult to separ…
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna +2
Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In pract…
Chained Prompting for Better Systematic Review Search Strategies
Fatima Nasser, Fouad Trad, Ammar Mohanna +2
Systematic reviews require the use of rigorously designed search strategies to ensure both comprehensive retrieval and minimization of bias. Conventional manual approaches, althoug…
AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Sina Mukalled +5
We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories…
Optimizing Deep Neural Networks using Safety-Guided Self Compression
Mohammad Zbeeb, Mariam Salman, Mohammad Bazzi +1
The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size wi…