PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Participants achieved near-chance accuracy (~50%) distinguishing real from AI-generated media across four modalities, with performance declining for faces, foreign languages, single modalities, and mixed-authenticity audiovisual clips.
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.
citing papers explorer
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli
Participants achieved near-chance accuracy (~50%) distinguishing real from AI-generated media across four modalities, with performance declining for faces, foreign languages, single modalities, and mixed-authenticity audiovisual clips.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD estimates local intrinsic dimension in high-D spaces by spectral filtering of the log-density Hessian via SLQ to isolate zero-curvature tangent directions.