ADMIT achieves 86% average attack success rate on RAG fact-checking at 0.93×10^{-6} poisoning rate across 4 retrievers, 11 LLMs, and 4 benchmarks while remaining robust to counter-evidence.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3roles
background 1polarities
background 1representative citing papers
G-Defense builds claim-centered graphs from sub-claims, applies RAG for evidence and competing explanations, then uses graph inference to detect fake news veracity and generate intuitive explanation graphs, claiming SOTA results.
Logical soundness is not a reliable criterion for neurosymbolic fact-checking with LLMs because it systematically diverges from human pragmatic inferences.
citing papers explorer
-
ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
ADMIT achieves 86% average attack success rate on RAG fact-checking at 0.93×10^{-6} poisoning rate across 4 retrievers, 11 LLMs, and 4 benchmarks while remaining robust to counter-evidence.
-
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
G-Defense builds claim-centered graphs from sub-claims, applies RAG for evidence and competing explanations, then uses graph inference to detect fake news veracity and generate intuitive explanation graphs, claiming SOTA results.
-
Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs
Logical soundness is not a reliable criterion for neurosymbolic fact-checking with LLMs because it systematically diverges from human pragmatic inferences.