Fine-grained taxonomic prompts substantially raise antisemitism-detection recall across four LLMs while lowering precision; larger conceptual resources add no further quantitative gain and post-Holocaust forms remain hardest.
Evaluating Large Language Models for Detecting Antisemitism
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism
Fine-grained taxonomic prompts substantially raise antisemitism-detection recall across four LLMs while lowering precision; larger conceptual resources add no further quantitative gain and post-Holocaust forms remain hardest.