arXiv Machine Learning By Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Sta\'nczak, Vered Shwartz, Siva Reddy

Value Drifts: Tracing Value Alignment During LLM Post-Training

Read the original on arXiv Machine Learning →

arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
22h ago

Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training

arXiv:2608. 16926v1 Announce Type: new Abstract: Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance.

By Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu