From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels
Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov +2
The paper introduces JADR, a protocol that examines a language model's internal Jacobian representations (J-space) to assess danger recognition before any response is generated, en…
cs.CL2026
ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation
Roman Prosvirnin, Sergei Kuznetsov, Seungmin Jin
Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to ex…