No AI summary available for this article.
Why It Matters
Fallacy-detection benchmarks pair fallacy classes with a single "valid" or "none" class that takes everything data collection did not label as a fallacy.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Fallacy-detection benchmarks pair fallacy classes with a single "valid" or "none" class that takes everything data collection did not label as a fallacy. This construction is misleading: a classifier can learn cues that do well on this class without learning to tell a fallacy from a correct argument. We show that the low false-positive rates benchmarks report are an artifact of how the class is built, not evidence of detection ability. The most informative negative for a fallacy is a correct argument using the same argumentation scheme, and such arguments are at most a few percent of the valid...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.18644v1 · Indexed about 1 hour ago