Papers by Massimiliano Pronesti
Query-driven Document-level Scientific Evidence Extraction from Biomedical Studies (2025.acl-long)
Copied to clipboard
Massimiliano Pronesti, Joao H Bettencourt-Silva, Paul Flanagan, Alessandra Pascale, Oisín Redmond, Anya Belz, Yufang Hou
| Challenge: | Systematic reviews are widely regarded as the gold standard in evidence-based medicine, heavily influencing medical decisions made by doctors, health authorities, and patients. |
| Approach: | They propose a retrieval-augmented generation framework to tackle the unique challenges of evidence extraction by leveraging forest plots from Cochrane systematic reviews. |
| Outcome: | The proposed framework outperforms existing methods by up to 10.3% in the F1 score on this task. |
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis (2026.acl-demo)
Copied to clipboard
Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao H Bettencourt-Silva, Gurdeep Singh Mannu, Spiros Denaxas, Rui Providencia, Anya Belz, Yufang Hou
| Challenge: | Existing systems that generate publication-ready forest plots from biomedical papers are fragmented and time-consuming. |
| Approach: | They propose a system that generates publication-ready forest plots directly from biomedical papers . autoforest automatically suggests ICO elements, extracts outcome data and performs statistical synthesis . authors demonstrate how the system can accelerate evidence synthesis and lower the barrier to conducting meta-analyses . |
| Outcome: | The proposed system accelerates evidence synthesis and lowers the barrier to meta-analyses. |
FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models (2026.acl-long)
Copied to clipboard
Javier Carnerero-Cano, Massimiliano Pronesti, Radu Marinescu, Tigran T. Tchrakian, James Barry, Jasmina Gajcin, Yufang Hou, Alessandra Pascale, Elizabeth M. Daly
| Challenge: | Large language models (LLMs) often produce factually incorrect responses. |
| Approach: | They propose a new method that adapts across domains without retraining and leverages structured feedback to generate a correction. |
| Outcome: | The proposed method outperforms baseline methods on a VELI5 dataset and several popular long-form factuality datasets. |
Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models can be substantially improved using outcome-level verification signals. |
| Approach: | They propose a framework where intermediate reasoning steps are checked by deterministic, rule-based verifiers. |
| Outcome: | The proposed framework achieves 20% higher F1 than state-of-the-art models and 6.5% higher than verifiable outcome rewards, with substantial gains in evidence grounding and logical coherence. |
Enhancing Study-Level Inference from Clinical Trial Papers via Reinforcement Learning-Based Numeric Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has framed this task as a textual inference task by retrieving relevant content fragments and inferring conclusions from them. |
| Approach: | They propose to extract structured numerical evidence and apply domain knowledge informed logic to derive outcome-specific conclusions. |
| Outcome: | The proposed approach outperforms general-purpose LLMs of over 400B parameters and achieves a 21% improvement in F1 score over retrieval-based systems. |