Finance Meets LLMs
What they can learn from each other
As a finance practitioner, and also an active researcher in LLMs, I’ve found many connections between the two fields, particularly in how they simulate possible future paths and assign value to outcomes.
Key Similarity
| Finance | LLMs | |
|---|---|---|
| Simulator | Options: Heston, local vol, VolGAN; HFT/ market making: order book/ flow, queue dynamics. | A pretrained language model generates possible future token sequences. |
| Sampling | Monte Carlo price paths; order, cancellation, and execution events. | Inference / rollout samples many possible reasoning trajectories. |
| Reward | Option payoff; trading PnL adjusted for risk, costs, and market impact. | A reward or verifier assigns value to each generated trajectory. |
| Data | Massive market data, but rare regimes and high-value signals remain scarce. | Massive training data, but specialized, high-quality data remain scarce. |
| Scaling Laws | Excess Return: market, size, value, etc. | Intelligence: compute, model size, data. |
| Correlation | Asset diversification. | Attention is all you need. |
| Residual | Signals unexplained by factors. | Loops refine hidden states for reasoning. |
| Safety | Control tail risk through stress tests and risk limits. | Control harmful behavior. |
| Scale & Infra | Options: pricing speed, Greeks, etc; HFT: latency, networking, co-location. | Inference: throughput, bandwidth, parallelism, serving. |
Key Difference
| Finance | LLMs | |
|---|---|---|
| Dimension | Traditionally low- to medium-dimensional. | Extremely high-dimensional |
| State space | Continuous in option; discrete / event-driven in HFT. | Discrete token space |
| Dynamics | Stochastic price dynamics or discrete market events. | Discrete autoregressive |
| Applications | Pricing, trading, hedging, and risk management | Reasoning, coding, and personal AI |
What They Can Learn from Each Other
Finance can learn from LLMs by moving beyond individually calibrated, low-dimensional models toward high-dimensional, multimodal market simulators learned jointly across assets, signals, and market states.
LLMs, in turn, can learn from finance by placing greater emphasis on safety, tail risk, uncertainty, stress testing, hard constraints, risk controls, and robustness when models fail.
In short, LLMs can help finance model a larger world, while finance can help LLMs handle failure.
Acknowledgment
Thanks to ChatGPT for helping refine the ideas and wording in this post.
Citation
@misc{deng2026_finance_LLM,
title ={{Finance Meets LLMs}},
author ={Wei Deng},
journal ={A Sampler's Blog},
year ={2026},
howpublished = {\url{https://www.weideng.org/posts/finance_llms/}}
}