English

Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models

Computation and Language 2023-10-09 v3 Machine Learning

Abstract

A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural language task using methods like fine-tuning, calibration or in-context learning. In this work, we propose an approach to adapt the prior class distribution to perform text classification tasks without the need for labelled samples and only few in-domain sample queries. The proposed approach treats the LLM as a black box, adding a stage where the model posteriors are calibrated to the task. Results show that these methods outperform the un-adapted model for different number of training shots in the prompt and a previous approach were calibration is performed without using any adaptation data.

Keywords

Cite

@article{arxiv.2307.06713,
  title  = {Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models},
  author = {Lautaro Estienne and Luciana Ferrer and Matías Vera and Pablo Piantanida},
  journal= {arXiv preprint arXiv:2307.06713},
  year   = {2023}
}
R2 v1 2026-06-28T11:29:21.742Z