From Natural Language to Executable Option Strategies via Large Language Models
This addresses a specific problem for traders and financial analysts by providing a more reliable method to generate option strategies from natural language, though it is incremental as it builds on existing LLM capabilities with a neuro-symbolic approach.
The paper tackles the challenge of translating natural-language trading intents into executable option strategies by introducing the Option Query Language (OQL), a domain-specific intermediate representation that improves execution accuracy and logical consistency over direct baselines.
Large Language Models (LLMs) excel at general code generation, yet translating natural-language trading intents into correct option strategies remains challenging. Real-world option design requires reasoning over massive, multi-dimensional option chain data with strict constraints, which often overwhelms direct generation methods. We introduce the Option Query Language (OQL), a domain-specific intermediate representation that abstracts option markets into high-level primitives under grammatical rules, enabling LLMs to function as reliable semantic parsers rather than free-form programmers. OQL queries are then validated and executed deterministically by an engine to instantiate executable strategies. We also present a new dataset for this task and demonstrate that our neuro-symbolic pipeline significantly improves execution accuracy and logical consistency over direct baselines.