KDD2024 - Enhancing Reasoning of Large Language Models through Reward-Guided Search and SelfTraining
595 views
About this video
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by videoExplains reward-guided search and self-training for enhancing reasoning in large language models. Training methods for improving LLM behavior through iterative feedback and exploration.
Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.