Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the field, where the highest quality models are only available as black-boxes through inference APIs. Even when the model weights are available, the computational cost of fine-tuning large LMs can be prohibitive for most practitioners. In this work, we present a lightweight method for adapting large LMs to new domains and tasks, assuming no access to their weights or intermediate activations. Our approach fine-tunes a small white-box LM and combines it with the large black-box LM at the probability level through a small network, learned on a small validation set. We validate our approach by adapting a large LM (OPT-30B) to several domains and a downstream task (machine translation), observing improved performance in all cases, of up to 9%, while using a domain expert 23x smaller.
@article{arxiv.2305.16876,
title = {CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models},
author = {Aitor Ormazabal and Mikel Artetxe and Eneko Agirre},
journal= {arXiv preprint arXiv:2305.16876},
year = {2023}
}
Comments
This previously appeared as arXiv:2205.12213v2, which was submitted as new by mistake