LLM能通过结构推理识别市场隐藏机制，而非仅依赖时间关联。
Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing
- 用混淆测试验证LLM是否基于因果推理识别市场模式。
- 无标签提示下仍达71.5%识别率，证明其捕捉结构规律能力。
- 适合金融建模、风险控制与模型机制研究者参考。
我们提出混淆测试方法，验证大语言模型是否通过因果推理识别结构性市场模式，而非仅依赖时间关联。在覆盖95.6%的标普500期权数据（242个交易日）上，测试三种做市商对冲约束模式（伽马持仓、股票归零、零日到期对冲）。使用仅提供原始伽马暴露值的无偏提示，模型检测准确率达71.5%。WHO-WHOM-WHAT因果框架迫使模型识别经济主体（做市商）、受影响方（方向性交易者）及结构机制（强制对冲）。关键发现：即使季度经济盈利变化，检测准确率仍稳定在91.2%，表明模型识别的是结构性约束而非盈利模式。当加入制度标签后，准确率升至100%，但71.5%的无偏结果证实了真正的模式识别能力。结果表明，LLM具备通过纯结构推理探测复杂金融机制的涌现能力，对系统化策略开发、风险管理和变压器架构如何处理金融市场动态有重要启示。
原文摘要 · Abstract (English)
We introduce obfuscation testing, a novel methodology for validating whether large language models detect structural market patterns through causal reasoning rather than temporal association. Testing three dealer hedging constraint patterns (gamma positioning, stock pinning, 0DTE hedging) on 242 trading days (95.6% coverage) of S&P 500 options data, we find LLMs achieve 71.5% detection rate using unbiased prompts that provide only raw gamma exposure values without regime labels or temporal context. The WHO-WHOM-WHAT causal framework forces models to identify the economic actors (dealers), affected parties (directional traders), and structural mechanisms (forced hedging) underlying observed market dynamics. Critically, detection accuracy (91.2%) remains stable even as economic profitability varies quarterly, demonstrating that models identify structural constraints rather than profitable patterns. When prompted with regime labels, detection increases to 100%, but the 71.5% unbiased rate validates genuine pattern recognition. Our findings suggest LLMs possess emergent capabilities for detecting complex financial mechanisms through pure structural reasoning, with implications for systematic strategy development, risk management, and our understanding of how transformer architectures process financial market dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。