Credence replaces Jaccard-F1 with Semantic-F1 for claim decomposition quality and proves convergence properties for rule-based and LLM-based repair under stated assumptions, reporting +15-32pp gains on three domain benchmarks.
Generating Literal and Implied Subquestions to Fact-check Complex Claims , url =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
RADAR assigns adversarial LLM agent roles (Politician, Scientist, Judge) to detect omission-based half-truths in fact verification, but the provided full text is from an unrelated hyperspectral imaging paper.
citing papers explorer
-
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis
Credence replaces Jaccard-F1 with Semantic-F1 for claim decomposition quality and proves convergence properties for rule-based and LLM-based repair under stated assumptions, reporting +15-32pp gains on three domain benchmarks.
-
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
RADAR assigns adversarial LLM agent roles (Politician, Scientist, Judge) to detect omission-based half-truths in fact verification, but the provided full text is from an unrelated hyperspectral imaging paper.