No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection

cs.CL

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: 11 pages, 5 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
• FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
• Credible, Unreliable or Leaked?: Evidence Verification for Enhanced Automated Fact-checking
• Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation
• A Survey on Automated Fact-Checking
• Chronologically Consistent Large Language Models
• Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web
• A Guide to Misinformation Detection Data and Evaluation
• QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims
• A Benchmark for Open-Domain Numerical Fact-Checking Enhanced by Claim Decomposition
• Benchmark Data Contamination of Large Language Models: A Survey

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering