SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models Paper • 2412.11605 • Published 8 days ago • 15
Learning Task Decomposition to Assist Humans in Competitive Programming Paper • 2406.04604 • Published Jun 7 • 4
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models Paper • 2406.16714 • Published Jun 24 • 10