2 papers
cs.AI2026
Reliability by design: quantifying and eliminating fabrication risk in LLMs. From generative to consultative AI: a comparative analysis in the legal domain and lessons for high-stakes knowledge bases
Alex Dantart
This paper examines how to make large language models reliable for high-stakes legal work by reducing hallucinations. It distinguishes three AI paradigms: (1) standalone generative…
cs.AI2026
Topo-RAG: Topology-aware retrieval for hybrid text-table documents
Alex Dantart, Marco Kóvacs-Navarro
In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Gene…