5 papers
Auxiliary uncertainty signals for LLM-assisted systematic review screening: a benchmark across eight Cohen drug-class reviews
Arya Rahgozar, Pouria Mortezaagha
Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty. We show that an auxiliary BE…
Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
Pouria Mortezaagha, Arya Rahgozar
Retrieval-Augmented Generation (RAG) systems for biomedical literature are typically evaluated using ranking metrics like Mean Reciprocal Rank (MRR), which measure how well the sys…
AI Co-Scientist for Knowledge Synthesis in Medical Contexts: A Proof of Concept
Arya Rahgozar, Pouria Mortezaagha
Research waste in biomedical science is driven by redundant studies, incomplete reporting, and the limited scalability of traditional evidence synthesis workflows. We present an AI…
From Chaos to Clarity: Schema-Constrained AI for Auditable Biomedical Evidence Extraction from Full-Text PDFs
Pouria Mortezaagha, Joseph Shaw, Bowen Sun +1
Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded…
An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastive Semantic Highlighting and LLM Judgment
Pouria Mortezaagha, Arya Rahgozar
Full-text screening is the major bottleneck of systematic reviews (SRs), as decisive evidence is dispersed across long, heterogeneous documents and rarely admits static, binary rul…