🧑‍🔬 Marco Valentino

🏛️ Affiliations

🎓University of SheffieldSheffield · United Kingdom2025–2026 · 38 papersEmployment since 2025 · Lecturer, Computer Sciencecurrent🔬Idiap Research InstituteMartigny-Combe · Switzerland2020–2025 · 45 papers🎓University of ManchesterManchester · United Kingdom2019–2023 · 19 papers🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland2021–2023 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards (2021 · 10 citations)
   Datasets that pair NLI items with human-written explanations are often treated as ground truth for training and judging models that reason step by step.
2. Decomposing Natural Logic Inferences for Neural NLI (2022 · 8 citations)
   The paper asks whether transformer NLI models represent the two features that natural logic uses to decide entailment.
3. Supporting Context Monotonicity Abstractions in Neural NLI Models (2021 · 5 citations)
   Neural NLI models still reason badly when a word is swapped for a broader or narrower one inside a downward monotone context, such as one created by negation or quantifiers like "every".

All works

13 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem ProvingProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetXin Quan et al.2024 · 52 citations
2. Improving Chain-of-Thought Reasoning via Quasi-Symbolic AbstractionsProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetLeonardo Ranaldi, Marco Valentino, Andre Freitas2025 · 42 citations
3. SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language ModelsProceedings of the 20th International Workshop on Semantic Evaluation (2026) · original ↗ · no summary yetMarco Valentino et al.2026 · 22 citations
4. A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with TransformersProceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · original ↗ · no summary yetJordan Meadows et al.2024 · 14 citations
5. Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical DefinitionsProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetLan Zhang, Marco Valentino, Andre Freitas2025 · 11 citations
6. Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold StandardsInternational Conference on Computational SemanticsMarco Valentino, Ian Pratt-Hartmann, André Freitas2021 · 10 citations
7. Decomposing Natural Logic Inferences for Neural NLIBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLPJulia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, et al.2022 · 8 citations
8. Interventional Probing in High Dimensions: An NLI Case StudyFindings of the Association for Computational Linguistics: EACL 2023 · original ↗ · no summary yetJulia Rozanova et al.2023 · 7 citations
9. Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language ModelsProceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetGabriele Maraia et al.2026 · 5 citations
10. Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical ReasoningarXiv:2506.10903 · original ↗ · no summary yetLan Zhang et al.2025 · 5 citations
11. MASA: LLM-Driven Multi-Agent Systems for AutoformalizationarXiv:2510.08988 · original ↗ · no summary yetLan Zhang, Marco Valentino, Andre Freitas2025 · 5 citations
12. Supporting Context Monotonicity Abstractions in Neural NLI ModelsWorkshops on Natural Logic Meets Machine Learning (NALOMA)Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, et al.2021 · 5 citations
13. Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver CompositionProceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetLei Xu et al.2026 · 2 citations

🤝 Co-authors here

4 co-authors with a page, the most papers together first.

• André Freitas ×3
• Deborah Ferreira ×2
• Julia Rozanova ×2
• Mokanarangan Thayaparan ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing ×2
• BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022
• International Conference on Computational Semantics: International Conference on Computational Semantics 2021
• Workshops on Natural Logic Meets Machine Learning (NALOMA): NALOMA 2021
• Findings of the Association for Computational Linguistics: EACL 2023
• Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
• Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
• Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 155 times (of the 141,840 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/marco-valentino/