AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignmentby Pankayaraj Pathmanathan, Udari Madhushani Sehwag,…
Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignmentby Peter Vamplew, Conor F Hayes, Cameron Foale,…
3DS: Decomposed Difficulty Data Selection’s Case Study on LLM Medical Domain Adaptationby Hongxin Ding, Yue…
Superficial Safety Alignment Hypothesisby Jianwei Li, Jung-Eun KimFirst submitted to arxiv on: 7 Oct 2024CategoriesMain:…
TopoFR: A Closer Look at Topology Alignment on Face Recognitionby Jun Dan, Yang Liu, Jiankang…
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspectiveby…
FormalAlign: Automated Alignment Evaluation for Autoformalizationby Jianqiao Lu, Yingjia Wan, Yinya Huang, Jing Xiong, Zhengying…
Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?by Xilin YangFirst submitted…
Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbationby Guozhi…
Toward General Instruction-Following Alignment for Retrieval-Augmented Generationby Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao,…