Megadose AI progress, ranked and analyzed.

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

· HF Daily Papers ·
Post-cutoff claims still showed potential contamination in 17.09% to 29.30% of cases.

The paper argues that dynamic benchmarks reduce contamination risk but do not make multimodal fact-checking evaluations clean by default. The authors find that some newer claims can still be checked using public information available before a model’s cutoff, either directly or by combining older evidence. In their tests, contamination inflated Macro-F1 by up to 11.34 points and could change system rankings. The paper was accepted at ACM Multimedia 2026. HF Daily Papers' note

score 4

Categories: Research