Andre Freitas

Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition EACL 2026 Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models CoNLL 2026 FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean ACL 2026 Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study AAAI 2026 Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering AAAI 2026 SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language Models SemEval 2026 Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness EACL 2026 Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs ACL 2025 Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions EMNLP 2025 CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment EMNLP 2025 Controlling Equational Reasoning in Large Language Models with Prompt Interventions AAAI 2025 Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations NAACL 2025 Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations ACL 2025 Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions ACL 2025 Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis AAAI 2025 LangVAE and LangSpace: Building and Probing for Language Model VAEs EMNLP 2025 MASA: LLM-Driven Multi-Agent Systems for Autoformalization EMNLP 2025 Montague semantics and modifier consistency measurement in neural language models COLING 2025 Neuro-Symbolic Natural Language Processing EMNLP 2025 PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement ACL 2025 Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder CoNLL 2025 Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference ACL 2025 SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning NAACL 2025 TRACE: Training and Inference-Time Interpretability Analysis for Language Models EMNLP 2025 A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference COLING 2024 Aligning Large and Small Language Models via Chain-of-Thought Reasoning EACL 2024 An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery ACL 2024 A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers NAACL 2024 Consistent Autoformalization for Constructing Mathematical Libraries EMNLP 2024 Diffusion Twigs with Loop Guidance for Conditional Graph Generation NeurIPS 2024 Does the Order Matter? Curriculum Learning over Languages COLING 2024 Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations ACL 2024 Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement EACL 2024 Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models COLING 2024 Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions EMNLP 2024 Formal Semantic Controls over Language Models COLING 2024 Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders NAACL 2024 Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series NeurIPS 2024 Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders EACL 2024 Inference to the Best Explanation in Large Language Models ACL 2024 Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks ACL 2024 Multi-Operational Mathematical Derivations in Latent Space NAACL 2024 Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions EACL 2024 Reasoning with Natural Language Explanations EMNLP 2024 Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models EMNLP 2024 SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials SemEval 2024 Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving EMNLP 2024 Interventional Probing in High Dimensions: An NLI Case Study EACL 2023 Learning Disentangled Representations for Natural Language Definitions EACL 2023 NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports EMNLP 2023 SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data SemEval 2023 Case-Based Abductive Natural Language Inference COLING 2022 Decomposing Natural Logic Inferences for Neural NLI EMNLP 2022 Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration AAAI 2022 Shallow Discourse Parsing for Open Information Extraction and Text Simplification COLING 2022 Symmetry-induced Disentanglement on Graphs NeurIPS 2022 Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective ACL 2022 TextGraphs 2022 Shared Task on Natural Language Premise Selection COLING 2022 To be or not to be an Integer? Encoding Variables for Mathematical Text ACL 2022 Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders EMNLP 2021 Does My Representation Capture X? Probe-Ably ACL 2021 Explainable Inference Over Grounding-Abstract Chains for Science Questions ACL 2021 STAR: Cross-modal [STA]tement [R]epresentation for selecting relevant mathematical premises EACL 2021 Unification-based Reconstruction of Multi-hop Explanations for Science Questions EACL 2021 What is SemEval evaluating? A Systematic Analysis of Evaluation Campaigns in NLP EMNLP 2021 Premise Selection in Natural Language Mathematical Texts ACL 2020 DBee: A Database for Creating and Managing Knowledge Graphs and Embeddings EMNLP 2019 Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment AAAI 2019 Identifying and Explaining Discriminative Attributes EMNLP 2019 Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks EMNLP 2019 Transforming Complex Sentences into a Semantic Hierarchy ACL 2019 A Survey on Open Information Extraction COLING 2018 Graphene: a Context-Preserving Open Information Extraction System COLING 2018 Graphene: Semantically-Linked Propositions in Open Information Extraction COLING 2018 SemEval-2017 Task 11: End-User Development using Natural Language SemEval 2017 SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News SemEval 2017 A Sentence Simplification System for Improving Relation Extraction COLING 2016