toxicity-reduction

Tag

Cards List
#toxicity-reduction

Detoxification for LLM: From Dataset Itself

arXiv cs.CL · 2026-04-22 Cached

Researchers propose HSPD, a corpus-level detoxification pipeline that rewrites toxic spans in pretraining data while preserving semantics, achieving state-of-the-art toxicity reduction on GPT-2 XL, LLaMA-2, OPT, and Falcon models.

0 favorites 0 likes
#toxicity-reduction

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation

arXiv cs.CL · 2026-04-20 Cached

This paper proposes CAP-TTA, a test-time adaptation framework that uses preconditioned LoRA updates triggered by bias-risk scores to mitigate toxicity and bias in large language models during narrative generation, achieving faster optimization and better fluency than standard baselines.

0 favorites 0 likes
← Back to home

Submit Feedback