SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper
•
2412.11605
•
Published
•
17
Lingxin AI
company
AI & ML interests
large language model, dialogue system
Recent Activity
View all activity
LingxinAI's activity
huangminlie
authored
a
paper
about 1 month ago
wdz10032
updated
a
model
12 months ago