Paper: arXiv 2512.17923

Authors: Christopher Regan, Ying Xie

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 2.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper’s mathematical complexity is low, focusing on causal logic (WHO→WHOM→WHAT) and gamma exposure metrics without advanced stochastic calculus or complex formulas. Empirical rigor is high, evidenced by a large dataset (242 days, 95.6% coverage), robust out-of-sample testing (obfuscation), and measurable performance metrics (71.5% detection rate, 91.2% validation).

Research Flowchart

  flowchart TD
  A["Research Goal: Validate if LLMs detect structural market patterns<br>via causal reasoning vs. temporal association"] --> B["Method: Obfuscation Testing"]
  B --> C["Data: S&P 500 Options<br>242 Trading Days, 95.6% Coverage"]
  C --> D["Computational Process: WHO-WHOM-WHAT Framework<br>Unbiased Prompts (Raw Gamma Values Only)"]
  D --> E{"Evaluation"}
  E --> F["Key Findings"]
  F --> F1["LLM Detection Rate: 71.5%<br>(Unbiased context)"]
  F --> F2["Detection Accuracy: 91.2%<br>(Stable across economic regimes)"]
  F --> F3["Context Effect: 100%<br>(With regime labels)"]

Cited References (43)

  1. The pricing of options and corporate liabilities (1973)
  2. Efficient capital markets: A review of theory and empirical work (1970)
  3. Market microstructure theory (1995)
  4. Empirical market microstructure (2007)
  5. Liquidity and market structure (1988)
  6. The impact of option hedging on the spot market volatility (2022) — link
  7. 0DTEs: Trading, Gamma Risk and Volatility Propagation (2025) — link
  8. Market Tremors: Quantifying Structural Risks in Modern Financial Markets (2021) — link
and 35 more
  1. Stock price clustering on option expiration dates (2005) — link
  2. Demand-based option pricing (2009) — link
  3. Asset fire sales (and purchases) in equity markets (2007)
  4. Is there price discovery in equity options? (2013)
  5. How markets slowly digest changes in supply and demand (2009)
  6. Market volatility and feedback effects from dynamic hedging (1997)
  7. Statistical arbitrage in the US equities market (2010)
  8. Ex-ante skewness and expected stock returns (2013) — link
  9. Why does the option to stock volume ratio predict stock returns? (2016)
  10. O/S: The relative trading activity in options and stock (2010)
  11. Language models are few-shot learners (2020)
  12. Chain-of-thought prompting elicits reasoning in large language models (2022)
  13. GPT-4 technical report (2023) — link
  14. Large language models are zero-shot reasoners (2022)
  15. Can ChatGPT forecast stock price movements? Return predictability and large language models — → 2304.07619
  16. FinGPT: Open-source financial large language models — → 2306.06031
  17. BloombergGPT: A large language model for finance (2023) — link
  18. Rebooting AI: Building artificial intelligence we can trust (2019)
  19. Beyond accuracy: Behavioral testing of NLP models with CheckList (2020) — link
  20. The adaptive markets hypothesis (2004)
  21. Gamma exposure and market dynamics (2019)
  22. The dark index: Measuring market-maker positioning (2020)
  23. Equity derivatives strategy: Gamma hedging flows and market impact (2017)
  24. The rise of zero days to expiration options: Market structure and implications (2023)
  25. 0DTE options: Market structure implications and intraday volatility (2023)
  26. Rule 15c3-1: Net capital rule for broker-dealers (2024)
  27. Rule 4210: Margin requirements (2024)
  28. Higher order G reeks (2007)
  29. Option markets and implied volatility: Past versus present (2009)
  30. The gamma trap (2013)
  31. Does option trading have a pervasive impact on underlying stock prices? (2022)
  32. Human Action: A Treatise on Economics (1949)
  33. Man, Economy, and State with Power and Market (1962)
  34. The SpotGamma Index: Measuring gamma exposure and market volatility (2021) — link
  35. Gamma exposure and the cross-section of stock returns (2017) — link

2 of 43 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.