Self-Adapting Language Models

Adam Zweiger, Jyothish Pari, Han Guo, Yoon Kim, Pulkit Agrawal

Keywords: llms, ml, adaptation, meta learning, synthetic data, finetuning, continual learning, reinforcement learning, knowledge editing

TL;DR: RL to train LLMs how to generate data and update themselves to adapt to new knowledge/tasks.

Abstract: Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce $\textbf{Se}$lf-$\textbf{A}$dapting $\textbf{L}$LMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives. Given a new input, the model produces a $\textit{self-edit}$ --- a generation that may restructure the information in different ways, specify optimization hyperparameters, or invoke tools for data augmentation and gradient-based updates. Through supervised finetuning (SFT), these self-edits result in persistent weight updates, enabling lasting adaptation. To train the model to produce effective self-edits, we use a reinforcement learning loop, using the downstream performance of the updated model as the reward signal. Unlike prior approaches that rely on separate adaptation modules or auxiliary networks, SEAL directly uses the model's generation to parameterize and control its own adaptation process. Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation in response to new data. Our website and code is available at https://jyopari.github.io/posts/seal.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 18523