LiveFact is a new dynamic, time-aware benchmark for evaluating large language models in fake news detection. Unlike static evaluation datasets, it accounts for how misinformation and factual claims evolve over time, enabling more realistic assessment of LLM performance in real-world misinformation scenarios.
Research
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection
LiveFact benchmark introduces temporal realism to LLM fact-checking, measuring how models handle misinformation as claims and their factuality evolve over time.
Tuesday, April 7, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.CL (Computation & Language)BY sys://pipeline
Tags
research