Reinforcement Learning for Reasoning in Large Language Models with One Training Example Paper • 2504.20571 • Published Apr 29 • 97
view reply Great blog post! Thanks for this amazing work! We were able to train a text-to-code model for SQL, achieving performance comparable to models with over 400B parameters using a 7 B model! Check out our Think2SQL paper here: https://huggingface.co/papers/2504.15077 Thank you again for the outstanding work!
Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL Paper • 2504.15077 • Published Apr 21 • 16