SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper
•
2412.11605
•
Published
•
17
huangminlie
huangminlie
AI & ML interests
None yet
Recent Activity
authored
a paper
27 days ago
SPaR: Self-Play with Tree-Search Refinement to Improve
Instruction-Following in Large Language Models
Organizations
huangminlie's activity
authored
a
paper
27 days ago