Uncertainty-Aware Web-Conditioned Scientific Fact-Checking

• URL: http://arxiv.org/abs/2604.11036v1
• Date: Mon, 13 Apr 2026 06:01:20 GMT
• Title: Uncertainty-Aware Web-Conditioned Scientific Fact-Checking
• Abstract summary: We present a pipeline centered on atomic predicate-argument decomposition and calibrated, uncertainty-gated corroboration.<n> atomic facts are aligned to local snippets via embeddings, verified by a compact evidence-grounded checker.<n>System supports both binary and tri-valued classification where it predicts labels from Supported, Refuted, NEI for three-way tasks.
• Score: 7.158918759352649
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific fact-checking is vital for assessing claims in specialized domains such as biomedicine and materials science, yet existing systems often hallucinate or apply inconsistent reasoning, especially when verifying technical, compositional claims against an evidence snippet under source and cost/latency constraints. We present a pipeline centered on atomic predicate-argument decomposition and calibrated, uncertainty-gated corroboration: atomic facts are aligned to local snippets via embeddings, verified by a compact evidence-grounded checker, and only facts with uncertain support trigger domain-restricted web search over authoritative sources. The system supports both binary and tri-valued classification where it predicts labels from Supported, Refuted, NEI for three-way tasks. We evaluate under two regimes, Context-Only (no web) and Context+Web (uncertainty-gated web corroboration); when retrieved evidence conflicts with the provided context, we abstain with NEI rather than overriding the context. On multiple benchmarks, our framework surpasses the strongest benchmarks. In our experiments, web corroboration was invoked for only a minority of atomic facts on average, indicating that external evidence is consulted selectively under calibrated uncertainty rather than routinely. Overall, coupling atomic granularity with calibrated, uncertainty-gated corroboration yields more interpretable and context-conditioned verification, making the approach well-suited to high-stakes, single-document settings that demand traceable rationales, predictable cost/latency, and conservative.

Related papers

• TriQua: Reconciling Granularity and Context in Factuality Evaluation [4.287837378537226]
  We introduce TriQua, a framework that flexibly models facts based on their complexity.<n>Simple claims are extracted as standard triples, while complex claims are represented as hyperrelational facts.<n>We propose TriQuaScore to quantify the factuality of these structured fact units.
  arXiv  Detail & Related papers  (2026-08-05T12:22:28Z)
• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding [63.71245376513854]
  We present SciLens, an evidence-conditioned atomic entailment framework for multimodal scientific claim verification.<n>SciLens decomposes each claim into central empirical atoms and background atoms, grounds the central atoms to modality-specific evidence witnesses, and predicts the final label.<n>For tables, atoms are grounded to rows, columns, cells, arithmetic relations, and table scope; for figures, they are grounded through panels, axes, legends, visual encodings, categories, trends, ranks, and qualifier checks.
  arXiv  Detail & Related papers  (2026-06-18T19:02:17Z)
• ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection [17.165016272480262]
  Verifiable claim detection asks whether a claim expresses a factual statement that can, in principle, be assessed against external evidence.<n>We propose Context-Driven Claim Detection (ContextClaim), a paradigm that advances retrieval to the detection stage.<n>We evaluate ContextClaim on two datasets covering different topics and text genres, the CheckThat! 2022 Twitter dataset and the PoliClaim political debate dataset.
  arXiv  Detail & Related papers  (2026-03-31T17:20:46Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents [8.49451413641847]
  We argue that as research generation becomes cheap, auditability becomes the bottleneck.<n>This perspective proposes claim-level auditability as a first-class design and evaluation target for deep research agents.
  arXiv  Detail & Related papers  (2026-02-14T19:39:15Z)
• SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence [60.202862987441684]
  We introduce scientific instruction following: the capability to solve problems while strictly adhering to the constraints that establish scientific validity.<n>Specifically, we introduce SciIF, a multi-discipline benchmark that evaluates this capability by pairing university-level problems with a fixed catalog of constraints.<n>By measuring both solution correctness and multi-constraint adherence, SciIF enables finegrained diagnosis of compositional reasoning failures.
  arXiv  Detail & Related papers  (2026-01-08T09:45:58Z)
• Towards Real-Time Fake News Detection under Evidence Scarcity [66.58597356379907]
  We propose Evaluation-Aware Selection of Experts (EASE), a novel framework for real-time fake news detection.<n>EASE adapts its decision-making process according to the assessed sufficiency of available evidence.<n>We introduce RealTimeNews-25, a new benchmark for evaluating model generalization on emerging news with limited evidence.
  arXiv  Detail & Related papers  (2025-10-13T11:11:46Z)
• Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification [18.20994425756688]
  Atomic Fact Extraction and Verification (AFEV) is a novel framework that iteratively decomposes complex claims into atomic facts.<n>AFEV achieves state-of-the-art performance in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2025-06-09T05:49:43Z)
• FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models [59.171510592986735]
  We propose FactReasoner, a new factuality assessor that relies on probabilistic reasoning to assess the factuality of a long-form generated response.<n>Our experiments on labeled and unlabeled benchmark datasets demonstrate clearly that FactReasoner improves considerably over state-of-the-art prompt-based approaches.
  arXiv  Detail & Related papers  (2025-02-25T19:01:48Z)
• TrendFact: A Benchmark for Explainable Hotspot Perception in Fact-Checking with Natural Language Explanation [9.221637941193606]
  We introduce TrendFact, the first benchmark capable of evaluating hotspot perception ability (HPA) and all fact-checking tasks.<n> TrendFact consists of 7,643 curated samples sourced from trending platforms and professional fact-checking datasets.<n>We also propose FactISR, a reasoning framework that integrates dynamic evidence augmentation with influence score-based iterative self-reflection.
  arXiv  Detail & Related papers  (2024-10-19T15:25:19Z)
• SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables [68.76415918462418]
  We present SCITAB, a challenging evaluation dataset consisting of 1.2K expert-verified scientific claims. Through extensive evaluations, we demonstrate that SCITAB poses a significant challenge to state-of-the-art models. Our analysis uncovers several unique challenges posed by SCITAB, including table grounding, claim ambiguity, and compositional reasoning.
  arXiv  Detail & Related papers  (2023-05-22T16:13:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.