Publications of Marco Valentino
2026
| Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study, , , and , in: The 40th Annual AAAI Conference on Artificial Intelligence, 2026 |
| Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering, , , , and , in: The 40th Annual AAAI Conference on Artificial Intelligence, 2026 |
2025
| A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models, , and , in: Findings of the ACL, 2025 |
| Controlling Equational Reasoning in Large Language Models with Prompt Interventions, , and , in: The 39th Annual AAAI Conference on Artificial Intelligence, 2025 |
| Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations, , and , in: Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, 2025 |
| Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations, , , and , in: 63rd Annual Meeting of the Association for Computational Linguistics, 2025 |
| Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions, , and , in: The 2025 Conference on Empirical Methods in Natural Language Processing (best resource paper award), 2025 |
| Improving chain-of-thought reasoning via quasi-symbolic abstractions, , , and , in: 63rd Annual Meeting of the Association for Computational Linguistics, 2025 |
| MASA: A Modular Framework for LLM-Driven Multi-Agent Systems for Autoformalization, , and , in: Demonstration at the 2025 Conference on Empirical Methods in Natural Language Processing, 2025 |
| On the Nature of Explanation: An Epistemological-Linguistic Perspective for Explanation-Based Natural Language Inference, and , in: Philosophy & Technology, 2025 |
| PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement, , , , and , in: Demonstration at 63rd Annual Meeting of the Association for Computational Linguistics, 2025 |
| SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning, , , , and , in: Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, 2025 |
2024
| A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference, , and , in: The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, 2024 |
| A Symbolic Framework for Systematic Evaluation of Mathematical Reasoning with Transformers, , , and , in: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
[URL] |
| Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement, , , and , in: The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024 |
| Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models, , and , in: The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, 2024 |
| Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders, , , , and , in: In Findings of the Association for Computational Linguistics: NAACL 2024, 2024 |
| Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders, , , , and , in: Findings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024 |
| Inference to the Best Explanation in Large Language Models, , , and , in: In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, 2024 |
| Multi-Operational Mathematical Derivations in Latent Space, , , and , in: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024 |
| Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions, , and , in: The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), 2024 |
| On the Nature of Explanation: An Epistemological-Linguistic Perspective for Explanation-Based Natural Language Inference, and , in: Philosophy & Technology, 2024 |
| Reasoning with Natural Language Explanations, and , in: In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, 2024 |
| SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials, , and , in: In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), 2024 |
| Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving, , , and , in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024 |
2023
| NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports, , , , , and , in: Proceedings of The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), 2023 |
| On Interventional Probing in High Dimensions: An NLI Case Study, , , and , in: Findings of the 17th European Chapter of the Association for Computational Linguistics, 2023 |
| SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data, , , , , and , in: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), Association for Computational Linguistics, 2023 |
[DOI] [URL] |
2022
| Case-Based Abductive Natural Language Inference, , and , in: Proceedings of the 29th International Conference on Computational Linguistics, 2022 |
[URL] |
| Decomposing Natural Logic Inferences for Neural NLI, , , , and , in: BlackBoxNLP: Workshop on analyzing and interpreting neural networks for NLP, 2022 |
| Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-Hop Inference, , , , and , in: Transactions of the Association for Computational Linguistics, 2022 |
[DOI] |
| Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration, , , and , in: Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022 |
| TextGraphs 2022 Shared Task on Natural Language Premise Selection, , , , and , in: Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing, 2022 |
[URL] |
| To be or not to be an Integer? Encoding Variables for Mathematical Text, , , , and , in: Findings of the ACL, 2022 |
2021
| Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards, , and , in: 14th International Conference on Computational Semantics, 2021 |
[URL] |
| Does My Representation Capture X? Probe-Ably, , , , and , in: 59th Annual Meeting of the Association for Computational Linguistics (Demonstration track), 2021 |
[URL] |
| Encoding Explanatory Knowledge for Zero-shot Science Question Answering, , , and , in: 14th International Conference on Computational Semantics, 2021 |
[URL] |
| Explainable Inference Over Grounding-Abstract Chains for Science Questions, , and , in: 59th Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2021 |
|
| Explainable Natural Language Reasoning via Conceptual Unification, , and , in: 16th conference of the European Chapter of the Association for Computational Linguistics (EACL), 2021 |
[URL] |
| Supporting Context Monotonicity Abstractions in Neural NLI Models, , , , and , in: Natural Logic Meets Machine Learning Workshop, 2021 |
[URL] |
| Unification-based Reconstruction of Multi-hop Explanations for Science Questions, , and , in: 16th conference of the European Chapter of the Association for Computational Linguistics, 2021 |
[URL] |