ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
Authors:
- Zhexin ZhangZZZhexin Zhang
- Hao SunHSHao Sun
- Minlie HuangMHMinlie Huang
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 10420-10438
Abstract
Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Holistic Approach to Undesired Content Detection in the Real WorldProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Toxicity in chatgpt: Analyzing persona-assigned language models2023
- ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation2023
- COLD: A Benchmark for Chinese Offensive Language Detection2022
- On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark2022
- Recipes for Building an Open-Domain Chatbot2021
- Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection2021
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019