conftrace_

model detoxification

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

toxicity reduction (3) large language model (3) activation steering (1) sample diversity (1) poisoned training data (1) language model safety (1) llm detoxification (1) toxic sample diversity (1) user safety (1) neural network editing (1)

Papers

Backdoor Mitigation by Distance-Driven Detoxification ICCV 2025 Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders EMNLP 2025 Detoxifying Large Language Models via the Diversity of Toxic Samples EMNLP 2025 Detoxifying Large Language Models via Knowledge Editing ACL 2024