English

CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models

Computation and Language 2023-05-29 v1

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-28T10:47:28.736Z