fact-verification

Tag

Cards List
#fact-verification

CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification

arXiv cs.CL · 2026-06-08 Cached

CRAFT is a unified counterfactual reasoning framework that improves tabular question answering and fact verification by constructing both original and counterfactual statements, extracting evidence from bidirectional reasoning paths, and integrating them via a weighted mechanism. Experiments show consistent improvements over baselines on WikiTQ and TabFact datasets.

0 favorites 0 likes
#fact-verification

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

arXiv cs.AI · 2026-06-04 Cached

This paper introduces CHARM, a framework for detecting and mitigating cascading hallucinations in multi-step agentic RAG pipelines, where early-stage errors propagate and amplify across reasoning steps. CHARM achieves an 89.4% cascade detection rate and 82.1% error propagation reduction across multiple benchmarks with low latency overhead.

0 favorites 0 likes
#fact-verification

From Snippets to Semantics: Rethinking Evidence Granularity for Multilingual Fact Verification

arXiv cs.CL · 2026-05-27 Cached

This paper introduces SEEK, a framework for semantic evidence extraction in multilingual fact verification, which constructs coherent evidence chunks from full articles and fine-tunes multilingual LLMs with LoRA, achieving up to 20% improvement in macro-F1 over baselines.

0 favorites 0 likes
#fact-verification

Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification

arXiv cs.CL · 2026-05-27 Cached

The paper introduces NEI-CAP, a diagnostic protocol to evaluate how 'Not Enough Information' examples are constructed in fact verification benchmarks, revealing that models trained on shortcut-prone NEI constructions fail to transfer to harder, semantically related insufficient evidence cases.

0 favorites 0 likes
#fact-verification

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

arXiv cs.AI · 2026-05-19 Cached

This paper uses EEG recordings to study neural dynamics when humans process AI-generated hallucinated content, revealing distinct cognitive patterns and differences between misjudged and correctly judged hallucinations.

0 favorites 0 likes
#fact-verification

Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

arXiv cs.CL · 2026-04-22 Cached

RADAR introduces a role-anchored multi-agent debate framework where Politician and Scientist agents adversarially reason over evidence to detect misleading half-truths, outperforming baselines on omission-aware fact verification.

0 favorites 0 likes
← Back to home

Submit Feedback