Fake Date Tests: Can We Trust In-sample Accuracy of LLMs in Macroeconomic Forecasting?

Alexander Eliseev, Sergei Seleznev

arXiv 12 Jan 2026 · Econometrics

arXiv:2601.07992 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Large language models (LLMs) are a type of machine learning tool that economists have started to apply in their empirical research. One such application is macroeconomic forecasting with backtesting of LLMs, even though they are trained on the same data that is used to estimate their forecasting performance. Can these in-sample accuracy results be extrapolated to the model's out-of-sample performance? To answer this question, we developed a family of prompt sensitivity tests and two members of this family, which we call the fake date tests. These tests aim to detect two types of biases in LLMs' in-sample forecasts: lookahead bias and context bias. According to the empirical results, none of the modern LLMs tested in this study passed our first test, signaling the presence of lookahead bias in their in-sample forecasts.

Citation extraction

appendix boundary found by appendix_command · 45% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

Showing the top 10 of 40 scored citations.