STAIR Research Group | Scalable & Trustworthy AI Research
STAIR Research Group | Scalable & Trustworthy AI Research
People
Projects
Talks
Publications
Light
Dark
Automatic
Junfeng Fang
Latest
Context-DPO: Aligning Language Models for Context-Faithfulness
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
Cite
×