Can I read Reinforcement Learning For Reasoning in Large Language Models With Training Example on EtoBox?

Reinforcement Learning For Reasoning in Large Language Models With Training Example by peacemakupe2010 is a document available to read on EtoBox.

What is Reinforcement Learning For Reasoning in Large Language Models With Training Example about?

This document presents a study on the effectiveness of reinforcement learning with verifiable reward using only one training example (1-shot RLVR) to enhance the mathematical reasoning capabilities of large language models (LLMs). The findings demonstrate significant performance improvements on mathematical benchmarks, achieving up to 73.6% accuracy on MATH500 with just one example, and highlight phenomena such as post-saturation generalization and cross-category generalization. The study emphasizes the imp

Author

peacemakupe2010

Language

EN