Saved in:
Bibliographic Details
Main Authors: Hu, Zhanhao, Piet, Julien, Zhao, Geng, Jiao, Jiantao, Wagner, David
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.18822
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916472312299520
author Hu, Zhanhao
Piet, Julien
Zhao, Geng
Jiao, Jiantao
Wagner, David
author_facet Hu, Zhanhao
Piet, Julien
Zhao, Geng
Jiao, Jiantao
Wagner, David
contents Current LLMs are generally aligned to follow safety requirements and tend to refuse toxic prompts. However, LLMs can fail to refuse toxic prompts or be overcautious and refuse benign examples. In addition, state-of-the-art toxicity detectors have low TPRs at low FPR, incurring high costs in real-world applications where toxic examples are rare. In this paper, we introduce Moderation Using LLM Introspection (MULI), which detects toxic prompts using the information extracted directly from LLMs themselves. We found we can distinguish between benign and toxic prompts from the distribution of the first response token's logits. Using this idea, we build a robust detector of toxic prompts using a sparse logistic regression model on the first response token logits. Our scheme outperforms SOTA detectors under multiple metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18822
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Toxicity Detection for Free
Hu, Zhanhao
Piet, Julien
Zhao, Geng
Jiao, Jiantao
Wagner, David
Computation and Language
Current LLMs are generally aligned to follow safety requirements and tend to refuse toxic prompts. However, LLMs can fail to refuse toxic prompts or be overcautious and refuse benign examples. In addition, state-of-the-art toxicity detectors have low TPRs at low FPR, incurring high costs in real-world applications where toxic examples are rare. In this paper, we introduce Moderation Using LLM Introspection (MULI), which detects toxic prompts using the information extracted directly from LLMs themselves. We found we can distinguish between benign and toxic prompts from the distribution of the first response token's logits. Using this idea, we build a robust detector of toxic prompts using a sparse logistic regression model on the first response token logits. Our scheme outperforms SOTA detectors under multiple metrics.
title Toxicity Detection for Free
topic Computation and Language
url https://arxiv.org/abs/2405.18822