Marco Valentino

102 papers A* 8A 1B 2C 1Journal 59Unranked 31

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models. CoRR Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto, Leonardo Ranaldi
2026	—	`conf`	Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition. EACL (Volume 1: Long Papers) Lei Xu, Pierre Beckmann, Marco Valentino, André Freitas
2026	—	`conf`	Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models. EACL (Volume 1: Long Papers) Gabriele Maraia, Leonardo Ranaldi, Marco Valentino, Fabio Massimo Zanzotto
2026	J	`jnl`	Decompose-and-Formalise: Recursively Verifiable Natural Language Inference. CoRR Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2026	J	`jnl`	Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models. CoRR Mingzi Cao, Xingwei Tan, Mahmud Elahi Akhter, Marco Valentino, Maria Liakata, Xi Wang, Nikolaos Aletras
2026	J	`jnl`	Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents. CoRR Xin Quan, Jiafeng Xiong, Marco Valentino, André Freitas
2026	A*	`conf`	Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study. AAAI Yingji Zhang, Marco Valentino, Danilo S. Carvalho, André Freitas
2026	J	`jnl`	Logic-Parametric Neuro-Symbolic NLI: Controlling Logical Formalisms for Verifiable LLM Reasoning. CoRR Ali Farjami, Luca Redondi, Marco Valentino
2026	A*	`conf`	Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering. AAAI Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, André Freitas
2026	J	`jnl`	Monotonic Reference-Free Refinement for Autoformalization. CoRR Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition. CoRR Lei Xu, Pierre Beckmann, Marco Valentino, André Freitas
2025	A*	`conf`	Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions. EMNLP Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning. CoRR Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	Compartmentalised Agentic Reasoning for Clinical NLI. CoRR Maël Jullien, Lei Xu, Marco Valentino, André Freitas
2025	A*	`conf`	Controlling Equational Reasoning in Large Language Models with Prompt Interventions. AAAI Jordan Meadows, Marco Valentino, André Freitas
2025	J	`jnl`	Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies. CoRR Maël Jullien, Marco Valentino, Leonardo Ranaldi, André Freitas
2025	—	`conf`	Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations. NAACL (Long Papers) Leonardo Ranaldi, Marco Valentino, André Freitas
2025	A*	`conf`	Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision. EMNLP Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Maria Liakata, Nikolaos Aletras
2025	J	`jnl`	Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision. CoRR Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Maria Liakata, Nikolaos Aletras
2025	—	`conf`	Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations. ACL (1) Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2025	J	`jnl`	Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations. CoRR Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2025	J	`jnl`	Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions. CoRR Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models. CoRR Feng He, Zhenyang Liu, Marco Valentino, Zhixue Zhao
2025	—	`conf`	Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions. ACL (1) Leonardo Ranaldi, Marco Valentino, André Freitas
2025	J	`jnl`	Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions. CoRR Leonardo Ranaldi, Marco Valentino, Alexander Polonsky, André Freitas
2025	J	`jnl`	Integrating Expert Knowledge into Logical Programs via LLMs. CoRR Franciszek Górski, Oskar Wysocki, Marco Valentino, André Freitas
2025	J	`jnl`	Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study. CoRR Yingji Zhang, Marco Valentino, Danilo S. Carvalho, André Freitas
2025	—	`conf`	MASA: LLM-Driven Multi-Agent Systems for Autoformalization. EMNLP (System Demonstrations) Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	MASA: LLM-Driven Multi-Agent Systems for Autoformalization. CoRR Lan Zhang, Marco Valentino, André Freitas
2025	J	`jnl`	Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering. CoRR Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, André Freitas
2025	—	`conf`	Neuro-Symbolic Natural Language Processing. EMNLP (Tutorial Abstracts) André Freitas, Marco Valentino, Danilo Silva de Carvalho
2025	J	`jnl`	OpenSIR: Open-Ended Self-Improving Reasoner. CoRR Wai-Chung Kwan, Joshua Ong Jun Leang, Pavlos Vougiouklis, Jeff Z. Pan, Marco Valentino, Pasquale Minervini
2025	—	`conf`	PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement. ACL (3) Xin Quan, Marco Valentino, Danilo S. Carvalho, Dhairya Dalal, André Freitas
2025	J	`jnl`	PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement. CoRR Xin Quan, Marco Valentino, Danilo S. Carvalho, Dhairya Dalal, André Freitas
2025	—	`conf`	Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference. ACL (Findings) Geonhee Kim, Marco Valentino, André Freitas
2025	—	`conf`	SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning. NAACL (Long Papers) Magdalena Wysocka, Danilo S. Carvalho, Oskar Wysocki, Marco Valentino, André Freitas
2025	J	`jnl`	The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference. CoRR Maël Jullien, Marco Valentino, André Freitas
2025	—	`conf`	Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems. ACL (1) Tharindu Madusanka, Marco Valentino, Iqra Zahid, Ian Pratt-Hartmann, Riza Batista-Navarro
2024	—	`conf`	A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference. LREC/COLING Mokanarangan Thayaparan, Marco Valentino, André Freitas
2024	J	`jnl`	A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference. CoRR Mokanarangan Thayaparan, Marco Valentino, André Freitas
2024	J	`jnl`	A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models. CoRR Geonhee Kim, Marco Valentino, André Freitas
2024	—	`conf`	A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers. NAACL-HLT Jordan Meadows, Marco Valentino, Damien Teney, André Freitas
2024	J	`jnl`	Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations. CoRR Leonardo Ranaldi, Marco Valentino, André Freitas
2024	—	`conf`	Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement. EACL (1) Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2024	J	`jnl`	Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement. CoRR Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2024	—	`conf`	Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models. LREC/COLING Julia Rozanova, Marco Valentino, André Freitas
2024	J	`jnl`	Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models. CoRR Julia Rozanova, Marco Valentino, André Freitas
2024	—	`conf`	Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders. NAACL-HLT (Findings) Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas
2024	—	`conf`	Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders. EACL (Findings) Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, André Freitas
2024	J	`jnl`	Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders. CoRR Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, André Freitas
2024	—	`conf`	Inference to the Best Explanation in Large Language Models. ACL (1) Dhairya Dalal, Marco Valentino, André Freitas, Paul Buitelaar
2024	J	`jnl`	Inference to the Best Explanation in Large Language Models. CoRR Dhairya Dalal, Marco Valentino, André Freitas, Paul Buitelaar
2024	—	`conf`	Multi-Operational Mathematical Derivations in Latent Space. NAACL-HLT Marco Valentino, Jordan Meadows, Lan Zhang, André Freitas
2024	—	`conf`	Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions. EACL (1) Marco Valentino, Danilo S. Carvalho, André Freitas
2024	—	`conf`	Reasoning with Natural Language Explanations. EMNLP (Tutorial Abstracts) Marco Valentino, André Freitas
2024	J	`jnl`	Reasoning with Natural Language Explanations. CoRR Marco Valentino, André Freitas
2024	—	`conf`	SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. SemEval@NAACL Maël Jullien, Marco Valentino, André Freitas
2024	J	`jnl`	SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. CoRR Maël Jullien, Marco Valentino, André Freitas
2024	J	`jnl`	SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning. CoRR Magdalena Wysocka, Danilo S. Carvalho, Oskar Wysocki, Marco Valentino, André Freitas
2024	A*	`conf`	Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. EMNLP Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2024	J	`jnl`	Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. CoRR Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas
2023	J	`jnl`	A Symbolic Framework for Systematic Evaluation of Mathematical Reasoning with Transformers. CoRR Jordan Meadows, Marco Valentino, Damien Teney, André Freitas
2023	J	`jnl`	Estimating the Causal Effects of Natural Logic Features in Neural NLI Models. CoRR Julia Rozanova, Marco Valentino, André Freitas
2023	J	`jnl`	Generating Mathematical Derivations with Large Language Models. CoRR Jordan Meadows, Marco Valentino, André Freitas
2023	J	`jnl`	Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders. CoRR Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas
2023	—	`conf`	Interventional Probing in High Dimensions: An NLI Case Study. EACL (Findings) Julia Rozanova, Marco Valentino, Lucas C. Cordeiro, André Freitas
2023	J	`jnl`	Interventional Probing in High Dimensions: An NLI Case Study. CoRR Julia Rozanova, Marco Valentino, Lucas C. Cordeiro, André Freitas
2023	J	`jnl`	Multi-Operational Mathematical Derivations in Latent Space. CoRR Marco Valentino, Jordan Meadows, Lan Zhang, André Freitas
2023	J	`jnl`	Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions. CoRR Marco Valentino, Danilo S. Carvalho, André Freitas
2023	A*	`conf`	NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports. EMNLP Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Dónal Landers, André Freitas
2023	J	`jnl`	NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports. CoRR Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas
2023	—	`conf`	SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data. SemEval@ACL Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas
2023	J	`jnl`	SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data. CoRR Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas
2022	B	`conf`	Case-Based Abductive Natural Language Inference. COLING Marco Valentino, Mokanarangan Thayaparan, André Freitas
2022	—	`conf`	Decomposing Natural Logic Inferences for Neural NLI. BlackboxNLP@EMNLP Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas
2022	J	`jnl`	Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference. Trans. Assoc. Comput. Linguistics Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas
2022	J	`jnl`	Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language. CoRR Maël Jullien, Marco Valentino, André Freitas
2022	J	`jnl`	Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers. CoRR Mokanarangan Thayaparan, Marco Valentino, André Freitas
2022	A*	`conf`	Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration. AAAI Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas
2022	J	`jnl`	Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI. CoRR Marco Valentino, André Freitas
2022	—	`conf`	To be or not to be an Integer? Encoding Variables for Mathematical Text. ACL (Findings) Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, Julia Rozanova, André Freitas
2021	J	`jnl`	Decomposing Natural Logic Inferences in Neural NLI. CoRR Julia Rozanova, Deborah Ferreira, Marco Valentino, Mokanarangan Thayaparan, André Freitas
2021	J	`jnl`	Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards. CoRR Marco Valentino, Ian Pratt-Hartmann, André Freitas
2021	—	`conf`	Does My Representation Capture X? Probe-Ably. ACL (demo) Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan, Marco Valentino, André Freitas
2021	J	`jnl`	Does My Representation Capture X? Probe-Ably. CoRR Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan, Marco Valentino, André Freitas
2021	J	`jnl`	Encoding Explanatory Knowledge for Zero-shot Science Question Answering. CoRR Zili Zhou, Marco Valentino, Donal Landers, André Freitas
2021	—	`conf`	Explainable Inference Over Grounding-Abstract Chains for Science Questions. ACL/IJCNLP (Findings) Mokanarangan Thayaparan, Marco Valentino, André Freitas
2021	J	`jnl`	Hybrid Autoregressive Solver for Scalable Abductive Natural Language Inference. CoRR Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas
2021	J	`jnl`	Supporting Context Monotonicity Abstractions in Neural NLI Models. CoRR Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas
2021	A	`conf`	Unification-based Reconstruction of Multi-hop Explanations for Science Questions. EACL Marco Valentino, Mokanarangan Thayaparan, André Freitas
2021	J	`jnl`	∂-Explainer: Abductive Natural Language Inference via Differentiable Convex Optimization. CoRR Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas
2020	B	`conf`	A Framework for Evaluation of Machine Reading Comprehension Gold Standards. LREC Viktor Schlegel, Marco Valentino, André Freitas, Goran Nenadic, Riza Batista-Navarro
2020	J	`jnl`	A Framework for Evaluation of Machine Reading Comprehension Gold Standards. CoRR Viktor Schlegel, Marco Valentino, André Freitas, Goran Nenadic, Riza Batista-Navarro
2020	J	`jnl`	A Survey on Explainability in Machine Reading Comprehension. CoRR Mokanarangan Thayaparan, Marco Valentino, André Freitas
2020	J	`jnl`	Explainable Natural Language Reasoning via Conceptual Unification. CoRR Marco Valentino, Mokanarangan Thayaparan, André Freitas
2020	J	`jnl`	ExplanationLP: Abductive Reasoning for Explainable Science Question Answering. CoRR Mokanarangan Thayaparan, Marco Valentino, André Freitas
2020	J	`jnl`	Unification-based Reconstruction of Explanations for Science Questions. CoRR Marco Valentino, Mokanarangan Thayaparan, André Freitas
2019	—	`conf`	Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks. TextGraphs@EMNLP Mokanarangan Thayaparan, Marco Valentino, Viktor Schlegel, André Freitas
2019	J	`jnl`	Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks. CoRR Mokanarangan Thayaparan, Marco Valentino, Viktor Schlegel, André Freitas
2018	—	`conf`	A Framework for Personalized and Adaptive Socially Assistive Robotics. WOA Silvia Rossi, Giovanni Ercolano, Luca Raggioli, Marco Valentino, Claudia Di Napoli
2018	C	`conf`	Adaptive Workflows of Home-Care Services. WETICE Claudia Di Napoli, Marco Valentino, Luca Sabatucci, Massimo Cossentino
2017	—	`conf`	Graph Databases for Designing High-Performance Speech Recognition Grammars. IWCS(2) Maria Di Maro, Marco Valentino, Anna Riccio, Antonio Origlia