Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Zhexin, Lu, Yida, Ma, Jingyuan, Zhang, Di, Li, Rui, Ke, Pei, Sun, Hao, Sha, Lei, Sui, Zhifang, Wang, Hongning, Huang, Minlie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.16444
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917828394745856
author Zhang, Zhexin
Lu, Yida
Ma, Jingyuan
Zhang, Di
Li, Rui
Ke, Pei
Sun, Hao
Sha, Lei
Sui, Zhifang
Wang, Hongning
Huang, Minlie
author_facet Zhang, Zhexin
Lu, Yida
Ma, Jingyuan
Zhang, Di
Li, Rui
Ke, Pei
Sun, Hao
Sha, Lei
Sui, Zhifang
Wang, Hongning
Huang, Minlie
contents The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner. In this paper, we propose ShieldLM, an LLM-based safety detector, which aligns with common safety standards, supports customizable detection rules, and provides explanations for its decisions. To train ShieldLM, we compile a large bilingual dataset comprising 14,387 query-response pairs, annotating the safety of responses based on various safety standards. Through extensive experiments, we demonstrate that ShieldLM surpasses strong baselines across four test sets, showcasing remarkable customizability and explainability. Besides performing well on standard detection datasets, ShieldLM has also been shown to be effective as a safety evaluator for advanced LLMs. ShieldLM is released at \url{https://github.com/thu-coai/ShieldLM} to support accurate and explainable safety detection under various safety standards.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16444
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
Zhang, Zhexin
Lu, Yida
Ma, Jingyuan
Zhang, Di
Li, Rui
Ke, Pei
Sun, Hao
Sha, Lei
Sui, Zhifang
Wang, Hongning
Huang, Minlie
Computation and Language
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner. In this paper, we propose ShieldLM, an LLM-based safety detector, which aligns with common safety standards, supports customizable detection rules, and provides explanations for its decisions. To train ShieldLM, we compile a large bilingual dataset comprising 14,387 query-response pairs, annotating the safety of responses based on various safety standards. Through extensive experiments, we demonstrate that ShieldLM surpasses strong baselines across four test sets, showcasing remarkable customizability and explainability. Besides performing well on standard detection datasets, ShieldLM has also been shown to be effective as a safety evaluator for advanced LLMs. ShieldLM is released at \url{https://github.com/thu-coai/ShieldLM} to support accurate and explainable safety detection under various safety standards.
title ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
topic Computation and Language
url https://arxiv.org/abs/2402.16444