Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models

TL;DR

This paper introduces a structured training and evaluation framework for large language models to improve financial decision-making in noisy markets, using curated datasets and simulation protocols.

Contribution

It presents a novel dataset, evaluation protocol, and training approach that enhance LLMs' trading performance and generalization in real-world financial environments.

Findings

Models trained with our framework outperform open-source baselines.

Open models exhibit risk-aware, competitive trading behavior.

Performance approaches frontier models at smaller scales.

Abstract

Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets lacking ground truth. We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets, verified by an AI committee, enriched with structured reasoning traces, and augmented to reduce shortcut learning. To evaluate whether performance on isolated MCQs generalizes to real-world trading, we introduce a two-stage protocol combining test-set evaluation with an MCQ-based chronological trading simulation. Extensive evaluations across market regimes provide statistically robust evidence that open models trained with our framework exhibit competitive, risk-aware behavior over time, outperform open-source baselines, and approach frontier-model performance at smaller scale. We release the dataset and evaluation framework to support further research.