collaborators

14 papers

cs.CL2026

Principles of Concept Representation in Sentence Encoders

Isabelle Mohr, John Dujany, Jonathan Souquet +1

What makes a sentence encoder produce good concept representations? We approach this through the lens of representational compositionality: an encoder supports a concept family onl…

cs.AI2026

Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning

João Pedro Gandarela, Thiago Rios, Stefan Menzel +1

Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret the continuous numerical output…

cs.LG2026

From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach

Nura Aljaafari, Danilo S. Carvalho, Andre Freitas

Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no s…

cs.CL2026

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder

Yingji Zhang, Danilo S. Carvalho, André Freitas

Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisatio…

cs.DB2026

Reflective Reasoning for SQL Generation

Isabelle Mohr, Joao Gandarela, John Dujany +1

Robust text-to-SQL over complex, real-world databases remains brittle even with modern LLMs: iterative refinement often introduces syntactic and semantic drift, corrections tend to…

cs.CL2026

Emergence and Localisation of Semantic Role Circuits in LLMs

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Despite displaying semantic competence, large language models' internal mechanisms that ground abstract semantic structure remain insufficiently characterised. We propose a method…