conftrace_

language model detoxification

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

controlled text generation (4) toxicity reduction (3) large language model (3) text detoxification (2) language model (2) contrastive learning (2) toxic text detection (1) hard negative mining (1) jailbreak resistance (1) adapter training (1)

Papers

Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models ACL 2025 Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing NAACL 2025 CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation ACL 2023 Controlled Text Generation with Hidden Representation Transformations ACL 2023 Self-Detoxifying Language Models via Toxification Reversal EMNLP 2023 Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models NeurIPS 2022 Language Model Detoxification in Dialogue with Contextualized Stance Control EMNLP 2022