PPaperPicks

Marco Valentino

25 papers at tracked venues · 12 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×9EMNLP ×6NAACL ×5AAAI ×3EACL ×2

Frequent coauthors

André Freitas
×21
Danilo S. Carvalho
×5
Leonardo Ranaldi
×4
Dhairya Dalal
×3
Lan Zhang
×3
Jordan Meadows
×3
Xin Quan
×3
Lei Xu
×2
Maël Jullien
×2
Xingwei Tan
×2
Mahmud Elahi Akhter
×2
Maria Liakata
×2

Papers

  1. Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
    EACL 2026 ·
    Lei Xu
    ,
    Pierre Beckmann
    , Marco Valentino,
    André Freitas
  2. Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models
    EACL 2026 ·
    Gabriele Maraia
    ,
    Leonardo Ranaldi
    , Marco Valentino,
    Fabio Massimo Zanzotto
  3. Compartmentalised Agentic Reasoning for Clinical NLI
    ACL 2026 ·
    Maël Jullien
    ,
    André Freitas
    , Marco Valentino,
    Lei Xu
  4. Dissecting Clinical Reasoning in Natural Language Inference for Large Language Models
    ACL 2026 ·
    Maël Jullien
    ,
    André Freitas
    , Marco Valentino,
    Leonardo Ranaldi
  5. Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models
    ACL 2026 ·
    Mingzi Cao
    ,
    Xingwei Tan
    ,
    Mahmud Elahi Akhter
    , Marco Valentino,
    Maria Liakata
    ,
    Xi Wang
    ,
    Nikolaos Aletras
  6. Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
    AAAI 2026 ·
    Yingji Zhang
    , Marco Valentino,
    Danilo S. Carvalho
    ,
    André Freitas
  7. Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering
    AAAI 2026 · Marco Valentino,
    Geonhee Kim
    ,
    Dhairya Dalal
    ,
    Zhixue Zhao
    ,
    André Freitas
  8. Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
    EMNLP 2025 ·
    Lan Zhang
    , Marco Valentino,
    André Freitas
  9. Controlling Equational Reasoning in Large Language Models with Prompt Interventions
    AAAI 2025 ·
    Jordan Meadows
    , Marco Valentino,
    André Freitas
  10. Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations
    NAACL 2025 ·
    Leonardo Ranaldi
    , Marco Valentino,
    André Freitas
  11. Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
    EMNLP 2025 ·
    Xingwei Tan
    , Marco Valentino,
    Mahmud Elahi Akhter
    ,
    Maria Liakata
    ,
    Nikolaos Aletras
  12. Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
    ACL 2025 ·
    Xin Quan
    , Marco Valentino,
    Louise A. Dennis
    ,
    André Freitas
  13. Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
    ACL 2025 ·
    Leonardo Ranaldi
    , Marco Valentino,
    André Freitas
  14. MASA: LLM-Driven Multi-Agent Systems for Autoformalization
    EMNLP 2025 ·
    Lan Zhang
    , Marco Valentino,
    André Freitas
  15. Neuro-Symbolic Natural Language Processing
    EMNLP 2025 ·
    André Freitas
    , Marco Valentino,
    Danilo Silva de Carvalho
  16. PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
    ACL 2025 ·
    Xin Quan
    , Marco Valentino,
    Danilo S. Carvalho
    ,
    Dhairya Dalal
    ,
    André Freitas
  17. Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
    ACL 2025 ·
    Geonhee Kim
    , Marco Valentino,
    André Freitas
  18. SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
    NAACL 2025 ·
    Magdalena Wysocka
    ,
    Danilo S. Carvalho
    ,
    Oskar Wysocki
    , Marco Valentino,
    André Freitas
  19. Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems
    ACL 2025 ·
    Tharindu Madusanka
    , Marco Valentino,
    Iqra Zahid
    ,
    Ian Pratt-Hartmann
    ,
    Riza Batista-Navarro
  20. A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers
    NAACL 2024 ·
    Jordan Meadows
    , Marco Valentino,
    Damien Teney
    ,
    André Freitas
  21. Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders
    NAACL 2024 ·
    Yingji Zhang
    , Marco Valentino,
    Danilo S. Carvalho
    ,
    Ian Pratt-Hartmann
    ,
    André Freitas
  22. Inference to the Best Explanation in Large Language Models
    ACL 2024 ·
    Dhairya Dalal
    , Marco Valentino,
    André Freitas
    ,
    Paul Buitelaar
  23. Multi-Operational Mathematical Derivations in Latent Space
    NAACL 2024 · Marco Valentino,
    Jordan Meadows
    ,
    Lan Zhang
    ,
    André Freitas
  24. Reasoning with Natural Language Explanations
    EMNLP 2024 · Marco Valentino,
    André Freitas
  25. Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving
    EMNLP 2024 ·
    Xin Quan
    , Marco Valentino,
    Louise A. Dennis
    ,
    André Freitas