Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning
This addresses a specific limitation in LLMs for compositional reasoning, though it appears incremental as it builds on existing tuning approaches.
The paper tackles the problem of large language models struggling with compositional tasks by proposing Re-Tuning, a method that recursively breaks down problems into subproblems. The result shows significantly higher accuracy and better GPU memory efficiency compared to state-of-the-art methods on tasks like integer addition, dynamic programming, and parity.
We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the solution depends on solving smaller instances of the same problem. We propose a natural approach to solve compositional tasks recursively. Our method, Re-Tuning, tunes models to break down a problem into subproblems, solve those subproblems, and combine the results. We show that our method significantly improves model performance on three representative compositional tasks: integer addition, dynamic programming, and parity. Compared to state-of-the-art methods that keep intermediate steps towards solving the problems, Re-Tuning achieves significantly higher accuracy and is more GPU memory efficient.