EMNLP 2023long findings0 citations
Geographical Erasure in Language Generation
Pola Schwöbel, Jacek Golebiowski, Michele Donini, Cedric Archambeau, Danish Pruthi
Abstract
Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capturing information about dominant groups. This imbalance can propagate into generated language. In this work, we study and operationalise a form of geographical erasure wherein language models underpredict certain countries. We demonstrate consistent instances of erasure across a range of LLMs. We discover that erasure strongly correlates with low frequencies of country mentions in the training corpus. Lastly, we mitigate erasure by finetuning using a custom objective.
large language modelsfairnesslanguage generationbiasworld knowledge
BibTeX
@inproceedings{
schw{\"o}bel2023geographical,
title={Geographical Erasure in Language Generation},
author={Pola Schw{\"o}bel and Jacek Golebiowski and Michele Donini and Cedric Archambeau and Danish Pruthi},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=EG7gjHZ8cm}
}