SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.
Hatebert: Retraining bert for abusive language detection in english
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.
Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.
citing papers explorer
-
LLM Safety From Within: Detecting Harmful Content with Internal Representations
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.
-
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.
-
Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task
Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.