Do LLMs Understand Limit Order Book Dynamics?
On the map: World models → World models for language agents
Abstract (arXiv)
A large language model (LLM) trained on synthetic limit order book (LOB) data achieves near perfect scores in generating valid sequences of LOB events. However, the LLM's implicit world model fails to learn the state of the LOB. This deficiency leads to biased estimates and spurious predictability in using the LLM to forecast future LOB events. Our analysis uses novel tests of an LLM's world model, extending prior work from deterministic settings to the stochastic dynamics needed for the LOB.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 0 of its 12 references that are in the map. First posted on arXiv 24 Aug 2026.
Builds on
0 of 12 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Are Large Language Models Temporally Grounded?
- 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
- 2026Recipes for Steering and Scaling LLMs via Sampling
- 2025When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
- 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
- 2024LLM Inference Unveiled: Survey and Roofline Model Insights
- 2025Do Large Language Models (LLMs) Understand Chronology?
- 2025Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls