Papers by Matteo Paganelli
GRI-QA: a Comprehensive Benchmark for Table Question Answering over Environmental Data (2025.findings-acl)
Copied to clipboard
Michele Luca Contalbo, Sara Pederzoli, Francesco Del Buono, Venturelli Valeria, Francesco Guerra, Matteo Paganelli
| Challenge: | Existing Table Question Answering systems for environmental reporting are complex and require specialized terminology and complex questions. |
| Approach: | They propose a test benchmark to evaluate Table QA approaches in the environmental domain. |
| Outcome: | The proposed benchmark reveals a significant gap between human and model performance in multi-step reasoning. |
Argument Relation Classification through Discourse Markers and Adversarial Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Argument relation classification (ARC) identifies supportive, contrasting and neutral relations between argumentative units. |
| Approach: | They propose an argument relation classifier that integrates knowledge of discourse markers into a pre-trained RoBERTa model. |
| Outcome: | The proposed model outperforms existing methods and learns discriminative sentence embeddings supporting the task. |
CLARIESG: An End-to-End System for ESG Analysis over Complex Tables in Corporate Reports (2026.eacl-demo)
Copied to clipboard
Marta Santacroce, Michele Luca Contalbo, Sara Pederzoli, Riccardo Benassi, Venturelli Valeria, Matteo Paganelli, Francesco Guerra
| Challenge: | Sustainability reports contain rich Environmental, Social and Governance information, but their heterogeneous layouts and complex multi-table structures pose major challenges for LLMs, especially for unit normalization, cross-document reasoning, and precise numerical computation. |
| Approach: | They propose an end-to-end system that couples robust table extraction with a structured prompting framework for multi-table filtering, normalization, and program-of-thought reasoning. |
| Outcome: | The proposed system outperforms standard prompting on multi-table benchmarks and provides transparent, auditable reasoning. |