| 2026 | AAAI | Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering. | Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, Andr Freitas |
| 2026 | AAAI | Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study. | Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Andr Freitas |
| 2026 | ACL | Emergence and Localisation of Semantic Role Circuits in LLMs. | Nura Aljaafari, Danilo S. Carvalho, Andr Freitas |
| 2026 | ACL | Dissecting Clinical Reasoning in Natural Language Inference for Large Language Models. | Mal Jullien, Andr Freitas, Marco Valentino, Leonardo Ranaldi |
| 2026 | ACL | Compartmentalised Agentic Reasoning for Clinical NLI. | Mal Jullien, Andr Freitas, Marco Valentino, Lei Xu |
| 2026 | ACL | FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean. | Jordan Meadows, Lan Zhang, Andr Freitas |
| 2026 | CoNLL | Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models. | Nura Aljaafari, Danilo S. Carvalho, Andr Freitas |
| 2026 | EACL | Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness. | Nura Aljaafari, Danilo S. Carvalho, Andr Freitas |
| 2026 | EACL | Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition. | Lei Xu, Pierre Beckmann, Marco Valentino, Andr Freitas |
| 2025 | AAAI | Controlling Equational Reasoning in Large Language Models with Prompt Interventions. | Jordan Meadows, Marco Valentino, Andr Freitas |
| 2025 | AAAI | Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis. | Joo Pedro Gandarela de Souza, Danilo S. Carvalho, Andr Freitas |
| 2025 | ACL | Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs. | Maxime Delmas, Magdalena Wysocka, Danilo Miranda Gusicuma, Andr Freitas |
| 2025 | ACL | Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference. | Geonhee Kim, Marco Valentino, Andr Freitas |
| 2025 | ACL | PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement. | Xin Quan, Marco Valentino, Danilo S. Carvalho, Dhairya Dalal, Andr Freitas |
| 2025 | ACL | Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations. | Xin Quan, Marco Valentino, Louise A. Dennis, Andr Freitas |
| 2025 | ACL | Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions. | Leonardo Ranaldi, Marco Valentino, Andr Freitas |
| 2025 | COLING | Montague semantics and modifier consistency measurement in neural language models. | Danilo Silva de Carvalho, Edoardo Manino, Julia Rozanova, Lucas C. Cordeiro, Andr Freitas |
| 2025 | EDBT | Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions. | Hafiz Tayyab Rauf, Alex Teodor Bogatu, Norman W. Paton, Andr Freitas |
| 2025 | EMNLP | CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment. | Nura Aljaafari, Danilo S. Carvalho, Andr Freitas |
| 2025 | EMNLP | TRACE: Training and Inference-Time Interpretability Analysis for Language Models. | Nura Aljaafari, Danilo S. Carvalho, Andr Freitas |
| 2025 | EMNLP | LangVAE and LangSpace: Building and Probing for Language Model VAEs. | Danilo S. Carvalho, Yingji Zhang, Harriet Unsworth, Andr Freitas |
| 2025 | EMNLP | Neuro-Symbolic Natural Language Processing. | Andr Freitas, Marco Valentino, Danilo Silva de Carvalho |
| 2025 | EMNLP | Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions. | Lan Zhang, Marco Valentino, Andr Freitas |
| 2025 | EMNLP | MASA: LLM-Driven Multi-Agent Systems for Autoformalization. | Lan Zhang, Marco Valentino, Andr Freitas |
| 2025 | IJCNN | Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data. | Thiago Csar Castilho Almeida, Gustavo Rosseto Leticio, Lucas Pascotti Valem, Andr Freitas, Daniel Carlos Guimares Pedronette |
| 2025 | NAACL | Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations. | Leonardo Ranaldi, Marco Valentino, Andr Freitas |
| 2025 | NAACL | SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning. | Magdalena Wysocka, Danilo S. Carvalho, Oskar Wysocki, Marco Valentino, Andr Freitas |
| 2024 | ACL | Inference to the Best Explanation in Large Language Models. | Dhairya Dalal, Marco Valentino, Andr Freitas, Paul Buitelaar |
| 2024 | ACL | Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations. | Leonardo Ranaldi, Giulia Pucci, Andr Freitas |
| 2024 | ACL | An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery. | Oskar Wysocki, Magdalena Wysocka, Danilo S. Carvalho, Alex Bogatu, Danilo Miranda Gusicuma, Maxime Delmas, Harriet Unsworth, Andr Freitas |
| 2024 | ACL | Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks. | Yingji Zhang, Danilo S. Carvalho, Andr Freitas |
| 2024 | COLING | Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models. | Julia Rozanova, Marco Valentino, Andr Freitas |
| 2024 | COLING | A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference. | Mokanarangan Thayaparan, Marco Valentino, Andr Freitas |
| 2024 | EACL | Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement. | Xin Quan, Marco Valentino, Louise A. Dennis, Andr Freitas |
| 2024 | EACL | Aligning Large and Small Language Models via Chain-of-Thought Reasoning. | Leonardo Ranaldi, Andr Freitas |
| 2024 | EACL | Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions. | Marco Valentino, Danilo S. Carvalho, Andr Freitas |
| 2024 | EACL | Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders. | Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, Andr Freitas |
| 2024 | EDBT | Deep Clustering for Data Cleaning and Integration. | Hafiz Tayyab Rauf, Andr Freitas, Norman W. Paton |
| 2024 | EMNLP | Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions. | Jordan Meadows, Tamsin James, Andr Freitas |
| 2024 | EMNLP | Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. | Xin Quan, Marco Valentino, Louise A. Dennis, Andr Freitas |
| 2024 | EMNLP | Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models. | Leonardo Ranaldi, Andr Freitas |
| 2024 | EMNLP | Reasoning with Natural Language Explanations. | Marco Valentino, Andr Freitas |
| 2024 | EMNLP | Consistent Autoformalization for Constructing Mathematical Libraries. | Lan Zhang, Xin Quan, Andr Freitas |
| 2024 | NAACL | A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers. | Jordan Meadows, Marco Valentino, Damien Teney, Andr Freitas |
| 2024 | NAACL | Multi-Operational Mathematical Derivations in Latent Space. | Marco Valentino, Jordan Meadows, Lan Zhang, Andr Freitas |
| 2024 | NAACL | Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders. | Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann, Andr Freitas |
| 2023 | EACL | Learning Disentangled Representations for Natural Language Definitions. | Danilo Silva de Carvalho, Giangiacomo Mercatali, Yingji Zhang, Andr Freitas |
| 2023 | EACL | Interventional Probing in High Dimensions: An NLI Case Study. | Julia Rozanova, Marco Valentino, Lucas C. Cordeiro, Andr Freitas |
| 2023 | EMNLP | NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports. | Mal Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Dnal Landers, Andr Freitas |
| 2022 | AAAI | EnnCore: End-to-End Conceptual Guarding of Neural Architectures. | Edoardo Manino, Danilo S. Carvalho, Yi Dong, Julia Rozanova, Xidan Song, Mustafa A. Mustafa, Andr Freitas, Gavin Brown, Mikel Lujn, Xiaowei Huang, Lucas C. Cordeiro |
| 2022 | AAAI | Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration. | Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, Andr Freitas |
| 2022 | ACL | To be or not to be an Integer? Encoding Variables for Mathematical Text. | Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, Julia Rozanova, Andr Freitas |
| 2022 | ACL | Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective. | Edoardo Manino, Julia Rozanova, Danilo S. Carvalho, Andr Freitas, Lucas C. Cordeiro |
| 2022 | COLING | Case-Based Abductive Natural Language Inference. | Marco Valentino, Mokanarangan Thayaparan, Andr Freitas |
| 2022 | DIAGRAMS | Why Scholars Are Diagramming Neural Network Models. | Guy Clarke Marshall, Caroline Jay, Andr Freitas |
| 2022 | EDBT | Voyager: Data Discovery and Integration for Onboarding in Data Science. | Alex Bogatu, Norman W. Paton, Mark Douthwaite, Andr Freitas |
| 2022 | LREC | PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics. | Jordan Meadows, Zili Zhou, Andr Freitas |
| 2022 | LREC | Text Classification and Prediction in the Legal Domain. | Minh-Quoc Nghiem, Paul Baylis, Andr Freitas, Sophia Ananiadou |
| 2021 | ACL | Does My Representation Capture X? Probe-Ably. | Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan, Marco Valentino, Andr Freitas |
| 2021 | ACL | Explainable Inference Over Grounding-Abstract Chains for Science Questions. | Mokanarangan Thayaparan, Marco Valentino, Andr Freitas |
| 2021 | DIAGRAMS | Understanding Scholarly Neural Network System Diagrams Through Application of VisDNA. | Guy Clarke Marshall, Caroline Jay, Andr Freitas |
| 2021 | DIAGRAMS | Structuralist Analysis for Neural Network System Diagrams. | Guy Clarke Marshall, Caroline Jay, Andr Freitas |
| 2021 | DIAGRAMS | Number and Quality of Diagrams in Scholarly Publications is Associated with Number of Citations. | Guy Clarke Marshall, Caroline Jay, Andr Freitas |
| 2021 | EACL | STAR: Cross-modal [STA]tement [R]epresentation for selecting relevant mathematical premises. | Deborah Ferreira, Andr Freitas |
| 2021 | EACL | Unification-based Reconstruction of Multi-hop Explanations for Science Questions. | Marco Valentino, Mokanarangan Thayaparan, Andr Freitas |
| 2021 | EMNLP | Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders. | Giangiacomo Mercatali, Andr Freitas |
| 2021 | ICDE | Cost-effective Variational Active Entity Resolution. | Alex Bogatu, Norman W. Paton, Mark Douthwaite, Stuart Davie, Andr Freitas |
| 2021 | ICWSM | What's Your Value of Travel Time? Collecting Traveler-Centered Mobility Data via Crowdsourcing. | Cristian Consonni, Silvia Basile, Matteo Manca, Ludovico Boratto, Andr Freitas, Tatiana Kovacikova, Ghadir Pourhashem, Yannick Cornet |
| 2021 | SAC | Microeconomic foundations of decentralised organisations. | Mauricio Jacobo-Romero, Andr Freitas |
| 2020 | ACL | Premise Selection in Natural Language Mathematical Texts. | Deborah Ferreira, Andr Freitas |
| 2020 | CIKM | SKG4J 2020: 1st International Workshop on Semantic and Knowledge Graph Advances for Journalism. | Tareq Al-Moslmi, Raphal Troncy, Andr Freitas, Davide Ceolin, Abdullatif Abolohom |
| 2020 | LREC | Natural Language Premise Selection: Finding Supporting Statements for Mathematical Text. | Deborah Ferreira, Andr Freitas |
| 2020 | LREC | A Framework for Evaluation of Machine Reading Comprehension Gold Standards. | Viktor Schlegel, Marco Valentino, Andr Freitas, Goran Nenadic, Riza Batista-Navarro |
| 2020 | NLDB | A User-centred Analysis of Explanations for a Multi-component Semantic Parser. | Juliano Efson Sales, Andr Freitas, Siegfried Handschuh |
| 2020 | SAC | Attentive recurrent text categorisation models using word-category cross embedding on financial comments. | Macedo Maia, Vivian Dos Santos Silva, Markus Endres, Andr Freitas, Siegfried Handschuh |
| 2019 | AAAI | Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment. | Vivian Dos Santos Silva, Andr Freitas, Siegfried Handschuh |
| 2019 | ACL | Transforming Complex Sentences into a Semantic Hierarchy. | Christina Niklaus, Matthias Cetto, Andr Freitas, Siegfried Handschuh |
| 2019 | EMNLP | Identifying and Explaining Discriminative Attributes. | Armins Stepanjans, Andr Freitas |
| 2019 | INLG | DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German. | Christina Niklaus, Matthias Cetto, Andr Freitas, Siegfried Handschuh |
| 2019 | INLG | MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions. | Christina Niklaus, Andr Freitas, Siegfried Handschuh |
| 2019 | IUI | Vajra: step-by-step programming with natural language. | Viktor Schlegel, Benedikt Lang, Siegfried Handschuh, Andr Freitas |
| 2018 | AAAI | Recognizing and Justifying Text Entailment Through Distributional Navigation on Definition Graphs. | Vivian Dos Santos Silva, Siegfried Handschuh, Andr Freitas |
| 2018 | COLING | Graphene: Semantically-Linked Propositions in Open Information Extraction. | Matthias Cetto, Christina Niklaus, Andr Freitas, Siegfried Handschuh |
| 2018 | COLING | Graphene: a Context-Preserving Open Information Extraction System. | Matthias Cetto, Christina Niklaus, Andr Freitas, Siegfried Handschuh |
| 2018 | COLING | A Survey on Open Information Extraction. | Christina Niklaus, Matthias Cetto, Andr Freitas, Siegfried Handschuh |
| 2018 | LREC | SemR-11: A Multi-Lingual Gold-Standard for Semantic Similarity and Relatedness for Eleven Languages. | Siamak Barzegar, Brian Davis, Manel Zarrouk, Siegfried Handschuh, Andr Freitas |
| 2018 | LREC | The SSIX Corpora: Three Gold Standard Corpora for Sentiment Analysis in English, Spanish and German Financial Microblogs. | Thomas Gaillat, Manel Zarrouk, Andr Freitas, Brian Davis |
| 2018 | LREC | A Multilingual Test Collection for the Semantic Search of Entity Categories. | Juliano Efson Sales, Siamak Barzegar, Wellington Franco, Bernhard Bermeitinger, Tiago Cunha, Brian Davis, Andr Freitas, Siegfried Handschuh |
| 2018 | LREC | Indra: A Word Embedding and Semantic Relatedness Server. | Juliano Efson Sales, Leonardo Souza, Siamak Barzegar, Brian Davis, Andr Freitas, Siegfried Handschuh |
| 2018 | LREC | Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition. | Vivian Dos Santos Silva, Andr Freitas, Siegfried Handschuh |
| 2018 | WWW | Question Answering Mediated by Visual Clues and Knowledge Graphs. | Fabrcio Firmino de Faria, Ricardo Usbeck, Alessio Sarullo, Tingting Mu, Andr Freitas |
| 2018 | WWW | WWW'18 Open Challenge: Financial Opinion Mining and Question Answering. | Macedo Maia, Siegfried Handschuh, Andr Freitas, Brian Davis, Ross McDermott, Manel Zarrouk, Alexandra Balahur |
| 2017 | NLDB | Composite Semantic Relation Classification. | Siamak Barzegar, Andr Freitas, Siegfried Handschuh, Brian Davis |
| 2016 | COLING | A Sentence Simplification System for Improving Relation Extraction. | Christina Niklaus, Bernhard Bermeitinger, Siegfried Handschuh, Andr Freitas |
| 2016 | EKAW | Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation. | Andr Freitas, Siamak Barzegar, Juliano Efson Sales, Siegfried Handschuh, Brian Davis |
| 2016 | EKAW | Word Tagging with Foundational Ontology Classes: Extending the WordNet-DOLCE Mapping to Verbs. | Vivian Dos Santos Silva, Andr Freitas, Siegfried Handschuh |
| 2016 | IDA | Determining Data Relevance Using Semantic Types and Graphical Interpretation Cues. | Eduardo Haruo Kamioka, Andr Freitas, Frederico Tommasi Caroli, Siegfried Handschuh |
| 2016 | LREC | NNBlocks: A Deep Learning Framework for Computational Linguistics Neural Network Models. | Frederico Tommasi Caroli, Andr Freitas, Joo Carlos Pereira da Silva, Siegfried Handschuh |
| 2015 | BIBE | Extending inner-ear anatomical concepts in the Foundational Model of Anatomy (FMA) ontology. | Yasar Khan, Muntazir Mehdi, Alokkumar Jha, Saleem Raza, Andr Freitas, Marggie Jones, Ratnesh Sahay |
| 2015 | SIGIR | DINFRA: A One Stop Shop for Computing Multilingual Semantic Relatedness. | Siamak Barzegar, Juliano Efson Sales, Andr Freitas, Siegfried Handschuh, Brian Davis |
| 2015 | SIGIR | Linse: A Distributional Semantics Entity Search Engine. | Juliano Efson Sales, Andr Freitas, Siegfried Handschuh, Brian Davis |
| 2014 | IUI | Natural language queries over heterogeneous linked data graphs: a distributional-compositional semantics approach. | Andr Freitas, Edward Curry |
| 2014 | NLDB | A Distributional Semantics Approach for Selective Reasoning on Commonsense Graph Knowledge Bases. | Andr Freitas, Joo Carlos Pereira da Silva, Edward Curry, Paul Buitelaar |
| 2014 | NLDB | On the Semantic Representation and Extraction of Complex Category Descriptors. | Andr Freitas, Rafael Vieira, Edward Curry, Danilo S. Carvalho, Joo Carlos Pereira da Silva |
| 2013 | BIBE | Towards a semantic representation for multi-scale finite element biosimulation experiments. | Andr Freitas, Margaret Jones, Kartik Asooja, Christos Bellos, Steve J. Elliott, Stefan Stenfelt, Panagiotis Hasapis, Christos Georgousopoulos, Torsten Marquardt, Nenad Filipovic, Stefan Decker, Ratnesh Sahay |
| 2013 | SIGIR | Answering natural language queries over linked data graphs: a distributional semantics approach. | Andr Freitas, Fabrcio Firmino de Faria, Sen O'Riain, Edward Curry |
| 2012 | SAC | A distributional approach for terminological semantic search on the Linked Data Web. | Andr Freitas, Edward Curry, Sen O'Riain |
| 2011 | NLDB | Querying Linked Data Using Semantic Relatedness: A Vocabulary Independent Approach. | Andr Freitas, Joo Gabriel Oliveira, Sen O'Riain, Edward Curry, Joo Carlos Pereira da Silva |
| 2011 | NLDB | Treo: Best-Effort Natural Language Queries over Linked Data. | Andr Freitas, Joo Gabriel Oliveira, Sen O'Riain, Edward Curry, Joo Carlos Pereira da Silva |