Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
cs.CL, cs.CR
Submitted: 2026-02-06
Updated: 2026-02-06
Code: https://github.com/unitaryai/detoxify
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Mistral 7B
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- VeFA: Vector-Based Feature Space Adaptation for Robust Model Fine-Tuning
- Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data