paper-with-me

홈 › Papers

Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing

2025-12-08 · Christopher Regan, Ying Xie arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.17923

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Inferring hidden forcing in a biological oscillator using Kolmogorov-Arnold networks

2026-06-07 · Julian Szereszewski, Facundo Fainstein, Leandro E. Fernandez, Gabriel B. Mindlin arxiv

Inferring the forces that drive a dynamical system from partial observations is a fundamental challenge across physics, particularly when distinct underlying mechanisms produce similar observable dynamics. Here we show t…

LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos

2026-07-14 · Julius Steiglechner, Lucas Mahler, Gabriele Lohmann arxiv

Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypotheses that explain observed behavior - remains poorly understood. Here, we…

Text Generation

Fast inference of latent space dynamics in huge relational event networks

2023-03-29 · Igor Artico, Ernst Wit

Relational events are a type of social interactions, that sometimes are referred to as dynamic networks. Its dynamics typically depends on emerging patterns, so-called endogenous variables, or external forces, referred t…

ClusteringGPU

LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting

2026-08-17 · Louen Pottier arxiv

We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular videos. At inference it lets a user push on the filmed object, rigid …

BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation

2026-06-29 · Ankur Samanta, Akshayaa Magesh, Tal Lancewicki, Ayush Jain 외 arxiv

Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environment. Acting rationally then requires inf…