Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data. In this paper, we explore whether we can go beyond human data on tasks where we have access to scalar feedback, for example, on math problems where one can verify correctness. To do so, we investigate a simple self-training method based on expectation-maximization, which we call \method, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the model on these samples, and (3) repeat this process a few times. Testing on advanced MATH reasoning and APPS coding benchmarks using PaLM-2 models, we find that \method{} scales favorably with model size and significantly surpasses fine-tuning only on human data. Overall, our findings suggest self-training with feedback can reduce dependence on human-generated data.

Authors

• Avi Singh
• John D Co-Reyes
• Rishabh Agarwal
• Ankesh Anand
• Piyush Patil
• Xavier Garcia
• Peter J Liu
• James Harrison
• Jaehoon Lee
• Kelvin Xu
• Aaron T Parisi
• Abhishek Kumar TCG Crest Kyungpook National University
• Alexander A Alemi
• Alex Rizkowsky
• Azade Nova
• Ben Adlam
• Bernd Bohnet
• Gamaleldin Fathy Elsayed
• Hanie Sedghi
• Igor Mordatch
• Isabelle Simpson
• Izzeddin Gur
• Jasper Snoek
• Jeffrey Pennington
• Jiri Hron
• Kathleen Kenealy
• Kevin Swersky University of Toronto
• Kshiteej Mahajan
• Laura A Culp
• Lechao Xiao
• Maxwell Bileschi
• Noah Constant
• Roman Novak
• Rosanne Liu
• Tris Warkentin
• Yamini Bansal
• Ethan Dyer
• Behnam Neyshabur
• Jascha Sohl-Dickstein
• Noah Fiedel

Keywords

No keywords are indexed for this paper.