DATEDGPT: Preventing Lookahead Bias in Large Language Models with Time-Aware Pretraining

By Yutong Yan, Raphael Tang, Zhenyu Gao, Wenxi Jiang, Yao Lu

Published 2026-07-23

Everscope rating

1435.3

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

5 / 5

About this paper

Methodology: Time-Aware Pretraining with Annual Data Cutoffs. Problem types: Natural Language Processing, Classification, Time Series Forecasting, Zero-shot Learning.

arXiv:2603.11838 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.