REVIEW 3 cited by
Toxicity Detection with Generative Prompt-based Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on corpus containing undesirable content, have the power to manifest biases and toxicity. However, recent studies imply that, as a remedy, LMs are also capable of identifying toxic content without additional fine-tuning. Prompt-methods have been shown to effectively harvest this surprising self-diagnosing capability. However, existing prompt-based methods usually specify an instruction to a language model in a discriminative way. In this work, we explore the generative variant of zero-shot prompt-based toxicity detection with comprehensive trials on prompt engineering. We evaluate on three datasets with toxicity labels annotated on social media posts. Our analysis highlights the strengths of our generative classification approach both quantitatively and qualitatively. Interesting aspects of self-diagnosis and its ethical implications are discussed.
Forward citations
Cited by 3 Pith papers
-
Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
EncoderLock modifies a small set of pre-trained encoder weights so that linear probing succeeds on authorized domains while failing on prohibited domains, in supervised, unsupervised, and zero-shot data scenarios.
-
WATCHED: A Web AI Agent Tool for Combating Hate Speech by Expanding Data
An AI agent combining retrieval, a BERT classifier, slang lookups, and policy guidelines reports macro F1 0.91 on a reannotated MetaHate test set, about 3 points above specialized baselines.
-
Towards Efficient and Explainable Hate Speech Detection via Model Distillation
A distilled Llama-3-8B model, trained with chain-of-thought rationales from Llama-3-70B, matches the large model's explanation quality and shows higher F1 on a hate speech test sample.
Discussion (0). Continue with ORCID to comment.