Papers › Unsupervised Improvement of Factual Knowledge in Language Models

Unsupervised Improvement of Factual Knowledge in Language Models

4 Apr 2023arXiv:2304.01597archive 2025-07-28

Nafis Sadeq, Byungkyu Kang, Prarit Lamba, Julian McAuley

Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for learning factual knowledge. In this work, we propose an approach for influencing MLM pretraining in a way that can improve language model performance on a variety of knowledge-intensive tasks. We force the language model to prioritize informative words in a fully unsupervised way. Experiments demonstrate that the proposed approach can significantly improve the performance of pretrained language models on tasks such as factual recall, question answering, sentiment analysis, and natural language inference in a closed-book setting.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

intuit/wmlm officialmentioned in paperpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingMasked Language ModelingNatural Language InferenceQuestion AnsweringSentiment Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections