Do LLMs Understand Limit Order Book Dynamics?
Quick summary
arXiv:2608.23706v1 Announce Type: new Abstract: 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 takeaways
- arXiv:2608.23706v1 Announce Type: new Abstract: 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.
Why it matters
“Do LLMs Understand Limit Order Book Dynamics?” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments