conftrace_

safety fine-tuning

9 papers

Explore in graph

Co-occurring keywords

large language model (13587) attack success rate (49) adversarial prompt (65) jailbreak attack (225) mechanistic interpretability (133) model safety (101) direct preference optimization (332) adversarial learning (1595) open-ended search (1) quality-diversity optimization (2)

Papers

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