PPaperPicks

André Freitas

41 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
  2. Compartmentalised Agentic Reasoning for Clinical NLI
  3. Dissecting Clinical Reasoning in Natural Language Inference for Large Language Models
  4. Emergence and Localisation of Semantic Role Circuits in LLMs
  5. FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
  6. Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
  7. Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering
  8. Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness
  9. Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs
  10. Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
  11. CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
  12. Controlling Equational Reasoning in Large Language Models with Prompt Interventions
  13. Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations
  14. Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
  15. Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions
  16. Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
  17. Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis
    AAAI 2025 ·
    João Pedro Gandarela de Souza
  18. LangVAE and LangSpace: Building and Probing for Language Model VAEs
  19. MASA: LLM-Driven Multi-Agent Systems for Autoformalization
  20. NEXUS-O: An Omni-Perceptive and -Interactive Model for Language, Audio, and Vision
  21. Neuro-Symbolic Natural Language Processing
    EMNLP 2025 · André Freitas
  22. PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
  23. Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
  24. SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
  25. TRACE: Training and Inference-Time Interpretability Analysis for Language Models
  26. TableDC: Deep Clustering for Tabular Data
  27. A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers
  28. An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery
  29. Consistent Autoformalization for Constructing Mathematical Libraries
  30. Deep Clustering for Data Cleaning and Integration
  31. Diffusion Twigs with Loop Guidance for Conditional Graph Generation
  32. Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations
  33. Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
  34. Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
  35. Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders
  36. Inference to the Best Explanation in Large Language Models
  37. Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
  38. Multi-Operational Mathematical Derivations in Latent Space
  39. Reasoning with Natural Language Explanations
  40. Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models
  41. Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving