Safety-Aware Fine-Tuning of Large Language Models

13 October 2024

Papers citing "Safety-Aware Fine-Tuning of Large Language Models"

4 / 4 papers shown

Title
Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data Adel ElZemity Budi Arief Shujun Li 29 0 0 15 May 2025
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety Zihan Guan Mengxuan Hu Ronghang Zhu Sheng R. Li Anil Vullikanti AAML 31 0 0 11 May 2025
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs Jan Betley Daniel Tan Niels Warncke Anna Sztyber-Betley Xuchan Bao Martín Soto Nathan Labenz Owain Evans AAML 78 9 0 24 Feb 2025
Process Reward Model with Q-Value Rankings W. Li Yixuan Li LRM 59 15 0 15 Oct 2024