toxicity reduction

Detoxification for LLM: From Dataset Itself ACL 2026 Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders EMNLP 2025 Controlling Large Language Models Through Concept Activation Vectors AAAI 2025 Detoxifying Large Language Models via the Diversity of Toxic Samples EMNLP 2025 DSCD: Large Language Model Detoxification with Self-Constrained Decoding EMNLP 2025 How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025 Large Language Models can Become Strong Self-Detoxifiers ICLR 2025 Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity ICLR 2025 Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents NAACL 2024 BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text NeurIPS 2024 Controlled Text Generation via Language Model Arithmetic ICLR 2024 Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning ACL 2024 Detoxifying Large Language Models via Knowledge Editing ACL 2024 Ethos: Rectifying Language Models in Orthogonal Parameter Space NAACL 2024 GrounDial: Human-norm Grounded Safe Dialog Response Generation EACL 2024 MBIAS: Mitigating Bias in Large Language Models While Retaining Context ACL 2024 Towards Aligning Language Models with Textual Feedback EMNLP 2024 Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding EMNLP 2024 Walking in Others’ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias EMNLP 2024 Adding Instructions during Pretraining: Effective way of Controlling Toxicity in Language Models EACL 2023 Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models ACL 2023 Detoxifying Online Discourse: A Guided Response Generation Approach for Reducing Toxicity in User-Generated Text ACL 2023 Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP 2023 Self-Detoxifying Language Models via Toxification Reversal EMNLP 2023 Using In-Context Learning to Improve Dialogue Safety EMNLP 2023