Saved in:
Bibliographic Details
Main Authors: Zhang, Xiao, Li, Miao, Wu, Ji
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01976
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Language models can learn sophisticated language understanding skills from fitting raw text. They also unselectively learn useless corpus statistics and biases, especially during finetuning on domain-specific corpora. In this paper, we propose a simple modification to causal language modeling called conditional finetuning, which performs language modeling conditioned on a context. We show that a context can "explain away" certain corpus statistics and make the model avoid learning them. In this fashion, conditional finetuning achieves selective learning from a corpus, learning knowledge useful for downstream tasks while avoiding learning useless corpus statistics like topic biases. This selective learning effect leads to less forgetting and better stability-plasticity tradeoff in domain finetuning, potentially benefitting lifelong learning with language models.