Self-Adapting Language Models

TL;DR

SEAL introduces a novel framework allowing large language models to self-adapt by generating their own fine-tuning data and update instructions, leading to improved knowledge incorporation and few-shot learning capabilities.

Contribution

This work presents the first self-adapting LLM framework that uses the model's own self-generated edits and reinforcement learning for persistent adaptation without auxiliary modules.

Findings

SEAL improves knowledge integration in LLMs.

SEAL enhances few-shot generalization performance.

Self-generated edits effectively update model weights.

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 Self-Adapting LLMs (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 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 with 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 own generation to control its 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. Our website and code is available at https://jyopari.github.io/posts/seal.