Coarse-Tuning Models of Code with Reinforcement Learning Feedback

no code implementations • 25 May 2023 • Abhinav Jain, Chima Adiole, Swarat Chaudhuri, Thomas Reps, Chris Jermaine

Our experiments show that RLCF raises the odds that an LLM-generated program compiles, is executable, and produces the right output on tests, often allowing LLMs to match the performance of 2x-8x larger LLMs.

Program Synthesis reinforcement-learning