2 papers
cs.CL2026
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency
Max Henning Höth, Kristian Kersting, Björn Deiseroth +1
Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully…
cs.CL2026
Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language Models
Björn Deiseroth, Björn Deiseroth, Max Henning Höth +3
Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic rather than verifiable evidence -- le…