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

TL;DR

DatedGPT introduces a family of time-aware language models trained on temporally partitioned data to prevent lookahead bias in financial forecasting, ensuring models only learn from data available up to their cutoff year.

Contribution

The paper presents DatedGPT, a novel approach to training large language models with strict temporal data boundaries, addressing lookahead bias in financial applications.

Findings

Models effectively bound knowledge by cutoff year

Competitive performance on standard benchmarks

Interactive demo for model comparison

Abstract

In financial backtesting, large language models pretrained on internet-scale data risk introducing lookahead bias that undermines their forecasting validity, as they may have already seen the true outcome during training. To address this, we present DatedGPT, a family of twelve 1.3B-parameter language models, each trained from scratch on approximately 100 billion tokens of temporally partitioned data with strict annual cutoffs spanning 2013 to 2024. We further enhance each model with instruction fine-tuning on both general-domain and finance-specific datasets curated to respect the same temporal boundaries. Perplexity-based probing confirms that each model's knowledge is effectively bounded by its data cutoff year, while evaluation on standard benchmarks shows competitive performance with existing models of similar scale. We provide an interactive web demo that allows users to query and compare responses from models across different cutoff years.