collaborators

7 papers

cs.CL2026

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing

Javier Marín

When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverg…

cs.AI2026

A Geometric Taxonomy of Hallucinations in LLMs

Javier Marín

Hallucinations in deployed language models can have real consequences for downstream decisions in domains such as healthcare, legal, and financial services. In production, detectio…

cs.AI2025

Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systems

Javier Marín

When retrieval-augmented generation (RAG) systems hallucinate, what geometric trace does this leave in embedding space? We introduce the Semantic Grounding Index (SGI), defined as…

cs.CL2025

Empirical Characterization of Temporal Constraint Processing in LLMs

Javier Marín

When deploying LLMs in agentic architectures requiring real-time decisions under temporal constraints, we assume they reliably determine whether action windows remain open or have…

cs.LG2025

Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach

Javier Marín

Loss Given Default (LGD) modeling faces a fundamental data quality constraint: 90% of available training data consists of proxy estimates based on pre-distress balance sheets rathe…

cs.AI2025

Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks

Javier Marín

We document empirical capability ceilings in decoder-only autoregressive language models across knowledge-intensive tasks. Systematic evaluation of OPT and Pythia model families (7…