Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time Input for Macro Factor Ranking (opens in new tab)
Forecasting benchmarks for retrieval-augmented LLMs routinely confound model capability with information leakage: features labeled with a target's timestamp are often not observable at the system's decision time. We study leakage-controlled equity factor ranking with a retrieval-augmented 7B open-source LLM forecaster. At each month-end from 2023-04 to 2026-03, the forecaster observes only decision-time information: lag-shifted FRED macro vari...
Read the original article