Implanting LLM’s Knowledge via Reading Comprehension Tree for Toxicity Detection
Authors:
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 947-962
Abstract
Hankun Kang, Tieyun Qian. Findings of the Association for Computational Linguistics ACL 2024. 2024.Keywords
This publication has 16 references indexed in Scilit:
- Handling Bias in Toxic Speech Detection: A SurveyACM Computing Surveys, 2023
- Large language models encode clinical knowledgeNature, 2023
- Large language models generate functional protein sequences across diverse familiesNature Biotechnology, 2023
- BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases2023
- KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications2023
- Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks2023
- Hate speech detection on Twitter using transfer learningComputer Speech & Language, 2022
- ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection2022
- A Survey on Automatic Detection of Hate Speech in TextACM Computing Surveys, 2018
- The nature of cyberbullying, and strategies for preventionComputers in Human Behavior, 2013