19 papers
Reflective Compositional Grounding for Natural-Language-to-SPARQL
Isabelle Mohr, John Dujany, Andre Freitas
Natural-language query generation over large knowledge graphs embodies the classical vocabulary problem in human-systems communication. Questions express concepts through wording a…
World Modeling in Transformers
Pierre Beckmann, Matthieu Queloz, Andre Freitas
Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT, a tran…
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
Nura Aljaafari, Andre Freitas
Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks and architectures. We introd…
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…
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…
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…
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…
elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings
Philip Osborne, Danilo S. Carvalho, André Freitas
We present elsciRL, an open-source Python library to facilitate the application of language solutions on reinforcement learning problems. We demonstrate the potential of our softwa…
TRACE: Training and Inference-Time Interpretability Analysis for Language Models
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on s…
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…
Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
Yingji Zhang, Marco Valentino, Danilo S. Carvalho +1
Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability.…
TRACE for Tracking the Emergence of Semantic Representations in Transformers
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Modern transformer models exhibit phase transitions during training, distinct shifts from memorisation to abstraction, but the mechanisms underlying these transitions remain poorly…
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…
PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
Xin Quan, Marco Valentino, Danilo S. Carvalho +2
A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the…
CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. While archit…
Interpreting token compositionality in LLMs: A robustness analysis
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-…
Inductive Learning of Logical Theories with LLMs: An Expressivity-Graded Analysis
João Pedro Gandarela, Danilo S. Carvalho, André Freitas
This work presents a novel systematic methodology to analyse the capabilities and limitations of Large Language Models (LLMs) with feedback from a formal inference engine, on logic…
Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies have attributed functional roles…
Transformer Normalisation Layers and the Independence of Semantic Subspaces
Stephen Menary, Samuel Kaski, Andre Freitas
Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logical…