# The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking

arXiv: https://arxiv.org/abs/2606.24627 · HTML: https://mlsanity.com/paper/2606.24627/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?](https://mlsanity.com/paper/2411.02400/) (2024)
- [DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation](https://mlsanity.com/paper/2412.13175/) (2024)
- [Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking](https://mlsanity.com/paper/2411.05375/) (2024)
- [COVE: COntext and VEracity prediction for out-of-context images](https://mlsanity.com/paper/2502.01194/) (2025)
- [Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers](https://mlsanity.com/paper/2506.13342/) (2025)
- [Optimizing Decomposition for Optimal Claim Verification](https://mlsanity.com/paper/2503.15354/) (2025)
- [The Missing Parts: Augmenting Fact Verification with Half-Truth Detection](https://mlsanity.com/paper/2508.00489/) (2025)
- [Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass](https://mlsanity.com/paper/2509.18901/) (2025)

## Abstract (arXiv)

Fact-checking systems built on LLMs achieve high verdict accuracy on standard benchmarks, yet routinely output Supports labels whose cited evidence does not license the claim. Structured decomposition is the natural way to inspect those warrants, but rigid extraction protocols strip the full-claim context that facets need. We introduce SIFT -- claim-conditioned re-scoring of extracted evidence spans against the full claim -- paired with WSP (Warranted Supports Proportion), an automatic NLI check that the cited warrant entails the claim. We evaluate on FEVER, SciFact, 5PILS, and DP across four open-source backbones. SIFT recovers accuracy on cells where naive decomposition costs up to 27.6 points, while raising WSP above direct prompting; WSP itself calibrates against human gold evidence at AUC 0.92 and precision 0.98.