2 papers
cs.CL2026
Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
Charles Moslonka, Hicham Randrianarivo, Arthur Garnier +1
Hallucinations in Large Language Model (LLM) outputs for Question Answering (QA) tasks can critically undermine their real-world reliability. This paper introduces a methodology fo…
gr-qc2025
Generalised Aichelburg-Sexl and Self-Force for photons
Abedennour Dib, Aymeric Garnier, Alessandro Spallicci
We generalise the Aichelburg-Sexl Stress-Energy-Momentum tensor for massless particles to include motion with angular velocity, introducing tensorial spherical harmonics. Further,…