Morning Edition · Wednesday, July 15, 2026Published at 1:45 AM EDT · New York

Researchers Scale Point-in-Time Language Models to Strip Lookahead Bias From Financial Backtests

Models trained on unrestricted internet corpora embed information from the future, and the paper studies how to build language models whose knowledge is bounded to a chosen historical date.

A new paper, Scaling Point-in-Time Language Models, addresses a problem that quietly invalidates a large class of research. Language models trained on unrestricted internet corpora inevitably absorb information from after any given date, wh…