Detoxifying language model outputs: combining multi-agent debates and reinforcement learning for improved summarization
- 29 April 2025
- journal article
- research article
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (3) , 2705-2736
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Fine-grained detoxification framework via instance-level prefixes for large language modelsNeurocomputing, 2024
- MedChatZH: A tuning LLM for traditional Chinese medicine consultationsComputers in Biology and Medicine, 2024
- DetoxLLM: A Framework for Detoxification with Explanations2024
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate2024
- ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs2024
- Detoxifying Large Language Models via Knowledge Editing2024
- A systematic review of hate speech automatic detection using natural language processingNeurocomputing, 2023
- Text Detoxification using Large Pre-trained Neural Models2021
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020