RSAT uses SFT on verified traces followed by GRPO with NLI faithfulness rewards to make 1-8B models produce verifiable table reasoning with cell citations, raising faithfulness 3.7x to 0.826.
arXiv preprint arXiv:2412.18004 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
In Agentic GraphRAG, cited evidence is necessary but not sufficient for accurate answers, as uncited traversal context and graph structure also affect results, requiring evaluation of the full retrieval trajectory.
citing papers explorer
-
RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners
RSAT uses SFT on verified traces followed by GRPO with NLI faithfulness rewards to make 1-8B models produce verifiable table reasoning with cell citations, raising faithfulness 3.7x to 0.826.
-
Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
In Agentic GraphRAG, cited evidence is necessary but not sufficient for accurate answers, as uncited traversal context and graph structure also affect results, requiring evaluation of the full retrieval trajectory.