Instruction-tuned large language models (LLMs) answer at greater length than a request needs. We ask whether a training-free controller inside the decoding loop can remove that surplus while preserving content, judged against the simplest possible baseline: truncating the model's own answer to the same length. An entro...
Mahmoud Alyosify, Mirna Imbabi, Eman Elkhamisi et al.· 0 citations
Large language models (LLMs) often generate responses longer than necessary, increasing inference latency and computational cost. While prompting can encourage conciseness, controlling output length without compromising response completeness remains challenging. Aggressive early stopping can reduce generation costs but...
Mahmoud Alyosify, Mirna Imbabi, Eman Elkhamisi et al.· 0 citations
This work presents an evidence-grounded agentic AI framework that connects liver and lesion segmentation with deterministic quantification and structured reporting, taking a step toward human-centered medical AI that prioritizes traceability and clinical relevance.
F. Mansour, Rahatara Ferdousi, Zyad Medhat Mahmoud Ashor et al.· 0 citations
An evidence-gated bilingual retrieval-augmented generation (RAG) framework for consumer banking search that operates entirely on local infrastructure and combines structured web-content refinement, hybrid dense-lexical retrieval, intent-aware evidence selection, cross-encoder reranking, and a three-outcome Answer / Rel...
Ahmed Rayyan, Rana Mahmoud Mohammed, A. Abdelmonem et al.· 0 citations
These findings show that robust multilingual healthcare evaluation requires explicit testing of register variation, uncertainty handling, and the provenance and invariance of adaptation labels.