Academic

Academic

Academic · 1 min

Improving Safety Alignment via Balanced Direct Preference Optimization

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. …

Shiji Zhao, Mengyang Wang, Shukun Xiong, Fangzhou Chen, Qihui Zhu, Shouwei Ruan, Yisong Xiao, Ranjie Duan, Xun Chen, XingXing Wei
26 views
Academic · 1 min

Improving LLM Predictions via Inter-Layer Structural Encoders

arXiv:2603.22665v1 Announce Type: new Abstract: The standard practice in Large Language Models (LLMs) is to base predictions on the final-layer token representations. Recent studies, however, …

Tom Ulanovski (Tel Aviv University), Eyal Blyachman (Tel Aviv University), Maya Bechler-Speicher (Meta)
47 views