Mechanistic Interpretability Meets Cognitive Linguistics: Modelling Locative Image Schemas in the Circuit Framework

Interaction, not dissection: reframing AI interpretability

It is argued that the ‘mission’ of mechanistic interpretability should be re-framed as the project of experimentally interacting with LLMs in order to study the behaviors and internal processes that emerge in virtue of these interactions.

How Are Large Language Models Fallible

Large Language Models (LLMs) operate within closed neural architectures, isolated from direct physical interaction with the external world. This lack of empirical grounding is a critical epistemic deficiency of empirical theories to explain the referential nature of LLM outputs and their hallucinatory fallibility. To a...

The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning

STRAT is introduced, which partitions the residual stream into orthogonal Data and Type subspaces and uses Type-based attention and gating to govern Data transformations and in arithmetic, STRAT reduces median OOD error 35-fold relative to a Transformer baseline.

Towards Structural Explainability for Reliable and Governable Large Language Models

LLM4XAI: Generative Models for Explainable AI Narratives

As AI systems are increasingly deployed in high-stakes domains, regulatory and societal demands for transparency and interpretability continue to grow. While classical Explainable AI (XAI) methods produce structured technical artifacts (e.g., feature attributions and counterfactual examples), these remain difficult to...

Emergent Reasoning in Large Language Models: A Systematic Evaluation Across Task Complexity

It is argued that emergent reasoning in LLMs is a product of three factors: model size, prompting approach, and evaluation metric, and proposed implications for designing benchmarks and assessing capabilities are proposed.