Skip to content
conftrace_

safety fine-tuning

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (6) attack success rate (2) adversarial prompt (2) jailbreak attack (2) mechanistic interpretability (2) adversarial attack (2) model safety (2) prompt engineering (2) direct preference optimization (2) adversarial learning (2)

Papers

Defending Speech-enabled LLMs Against Adversarial Jailbreak Threats Interspeech 2025 Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts? ICLR 2025 How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025 Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models NAACL 2025 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025 A StrongREJECT for Empty Jailbreaks NeurIPS 2024 MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024 Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NeurIPS 2024 Refusal in Language Models Is Mediated by a Single Direction NeurIPS 2024 What Makes and Breaks Safety Fine-tuning? A Mechanistic Study NeurIPS 2024