APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation

TL;DR

APE is a selective fine-tuning method for large language models that explores multiple parameter updates, accepting only those that improve performance, leading to significant gains with minimal resources.

Contribution

It introduces a novel selective fine-tuning approach inspired by evolutionary principles, enhancing model adaptation stability and efficiency.

Findings

33.9% BLEU improvement on news summarization

36.2% perplexity reduction

Achieves performance gains with minimal computational resources

Abstract

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization principles, APE evaluates multiple candidate parameter updates through fine-tuning on small data subsets and accepts only those exceeding a performance threshold. Unlike standard fine-tuning that follows single gradient directions, APE implements a filtered selection process that prevents destabilizing parameter changes while enabling systematic improvement. Our method achieves 33.9\% BLEU improvement and 36.2\% perplexity reduction on news summarization tasks while using minimal computational resources. The approach provides a practical framework for controlled model adaptation that balances performance gains with representational stability.