Paper: arXiv 2508.21285

Authors: Hui Chen, Antoine Didisheim, Mohammad, Pourmohammadi, Luciano Somoza, Hanqing Tian

Abstract

Emerging techniques in computer science make it possible to “brain scan” large language models (LLMs), identify the plain-English concepts that guide their reasoning, and steer them while holding other factors constant. We show that this approach can map LLM-generated economic forecasts to concepts such as sentiment, technical analysis, and timing, and compute their relative importance without reducing performance. We also show that models can be steered to be more or less risk-averse, optimistic, or pessimistic, which allows researchers to correct or simulate biases. The method is transparent, lightweight, and replicable for empirical research in the social sciences.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper introduces an innovative application of computer science techniques (Sparse Auto-Encoders) to financial LLM tasks, allowing for interpretability and feature steering in portfolio allocation and return prediction. While the underlying mathematical derivations of the SAE are primarily referenced from CS literature rather than developed here, the empirical validation across historical news datasets and asset allocation prompts is thorough and highly rigorous.

Research Flowchart

  flowchart TD
    A["Research Goal:<br>Interpret & steer LLM economic forecasts via 'brain scanning'"] --> B["Inputs:<br>LLM prompts, macroeconomic data & economic concepts"]
    
    B --> C["Concept Identification:<br>Map model activations to concepts (Sentiment, Risk, Timing)"]
    
    C --> D["Computational Processes:<br>Calculate concept importance & apply steering vectors"]
    
    D --> E["Findings: Quantified Drivers<br>Mapped forecasts to key concepts without loss of accuracy"]
    D --> F["Findings: Bias & Risk Control<br>Successfully steered model optimism & risk aversion"]

Cited References (365)

  1. Asset embeddings (2024)
  2. Attention is all you need (2017)
  3. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis (1987)
  4. Improving Text Embeddings with Large Language Models (2023) — link
  5. Some methods of classification and analysis of multivariate observations (1967)
  6. The virtue of complexity in return prediction (2024)
  7. Apt or “aipt”? the surprising dominance of large factor models (2024)
  8. Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus? (2023) — link
and 357 more
  1. Using principal components for estimating logistic regression with high-dimensional multicollinear data (2006)
  2. Comparing emotions in ChatGPT answers and human answers to the coding questions on Stack Overflow (2024)
  3. Scaling and evaluating sparse autoencoders (2024) — link
  4. Route sparse autoencoder to interpret large language models (2025) — link
  5. Performance hypothesis testing with the Sharpe and Treynor measures (1981)
  6. Text as data (2019)
  7. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks (2011)
  8. Giving content to investor sentiment: The role of media in the stock market (2007)
  9. Economic representations (2025)
  10. Is AI Reasoning Useful in Finance? (2025)
  11. Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies (2023) — link
  12. Out of the (black) box: Ai as conditional probability (2024)
  13. Out of One, Many: Using Language Models to Simulate Human Samples (2023) — link
  14. Generative Agents: Interactive Simulacra of Human Behavior (2023) — link
  15. The Structure of Economic News (2020)
  16. Empirical Asset Pricing via Machine Learning (2020)
  17. Autoencoder Asset Pricing Models (2021)
  18. Expected Returns and Large Language Models (2022)
  19. Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models — → 2304.07619
  20. Lookahead Bias in Pretrained Language Models (2024)
  21. AI’s Predictable Memory and Its Implications for Finance (2025)
  22. Performance Hypothesis Testing with the Sharpe Ratio (2003)
  23. Performance hypothesis testing with the Sharpe ratio (2003)
  24. AI ’s Predictable Memory and its Implications for Finance (2025)
  25. The Memorization Problem: Can We Trust LLMs’ Economic Forecasts? (2025)
  26. Limitations of language models in arithmetic and symbolic induction (2022)
  27. Business news and business cycles (2024)
  28. Thought confidence as a determinant of persuasion: the self-validation hypothesis. (2002)
  29. A self-validation perspective on the mere thought effect (2011)
  30. Large Language Models are Zero-Shot Reasoners (2022)
  31. Language models are unsupervised multitask learners (2019)
  32. Emergent Abilities of Large Language Models (2022)
  33. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025)
  34. AI and Finance (2024)
  35. Generative AI for economic research: Use cases and implications for economists (2023)
  36. Factor models, machine learning, and asset pricing (2022)
  37. Artificial intelligence, firm growth, and product innovation (2024)
  38. Intelligent financial system: how AI is transforming finance (2024)
  39. Machine learning as a tool for hypothesis generation (2024)
  40. Ideas are dimes a dozen: Large language models for idea generation in innovation (2023)
  41. Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers (2024) — link
  42. Predicting Results of Social Science Experiments Using Large Language Models (2024)
  43. Surveying Generative AI’s Economic Expectations (2023)
  44. ChatGPT and Perception Biases in Investments: An Experimental Study (2024)
  45. Displacement or Augmentation? The Effects of AI on Workforce Dynamics and Firm Value (2024)
  46. The Costs of Housing Regulation: Evidence From Generative Regulatory Measurement (2023)
  47. Identifying FinTech innovations using BERT (2020)
  48. Covenant AI -New Insights into Covenant Violations (2024)
  49. Assessing look-ahead bias in stock return predictions generated by gpt sentiment analysis — → 2309.17322
  50. Large language models: An applied econometric framework (2025)
  51. Entity Neutering (2025)
  52. Sparse autoencoders find highly interpretable features in language models (2023) — link
  53. AI Democratization, Return Predictability, and Trading Inequality (2023)
  54. Labor Space: A Unifying Representation of the Labor Market via Large Language Models (2024)
  55. A semantic approach to financial fundamentals (2020)
  56. Asset embeddings (2023)
  57. Tracking retail investor activity (2021)
  58. An introduction to prospect theory (1992)
  59. Predicting volatility using the Markov-switching multifractal model: Evidence from S&P 100 index and equity options (2013)
  60. The pricing of options and corporate liabilities (1973)
  61. Another look at models of the short-term interest rate (1996)
  62. Distrust or speculation? The socioeconomic drivers of US cryptocurrency investments (2021)
  63. Boys will be boys: Gender, overconfidence, and common stock investment (2001)
  64. The equity market implications of the retail investment boom (2021)
  65. An intertemporal capital asset pricing model (1973)
  66. Economic uncertainty, disagreement, and credit markets (2014)
  67. Economic uncertainty, disagreement, and credit markets (2014)
  68. A theory of overconfidence, self-attribution, and security market under-and over-reactions (1997)
  69. Why do (some) households trade so much? (2011)
  70. Limited asset market participation and the elasticity of intertemporal substitution (2002)
  71. Portfolio choices, firm shocks, and uninsurable wage risk (2018)
  72. Belief disagreement and portfolio choice (2018)
  73. The price of sin: The effects of social norms on markets (2009)
  74. Forecasting the distribution of option returns (2017)
  75. Do individual investors have asymmetric information based on work experience? (2011)
  76. Statistical applications of the multivariate skew normal distribution (1999)
  77. Hedging, familiarity and portfolio choice (2006)
  78. Preferred risk habitat of individual investors (2010)
  79. Who are the value and growth investors? (2017)
  80. Down or out: Assessing the welfare costs of household investment mistakes (2007)
  81. Heterogeneity and portfolio choice: Theory and evidence (2010)
  82. The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets (1975)
  83. Capital asset prices: A theory of market equilibrium under conditions of risk (1964)
  84. Liquidity preference as behavior towards risk (1958)
  85. The utility of wealth (1952)
  86. Maxing out: Stocks as lotteries and the cross-section of expected returns (2011)
  87. The behavior of individual investors (2013)
  88. Just how much do individual investors lose by trading? (2009)
  89. The joint dynamics of investor beliefs and trading during the COVID-19 crash (2021)
  90. The End of the Crypto-Diversification Myth (2022)
  91. The wisdom of the robinhood crowd (2020)
  92. Flattening the illiquidity curve: Retail trading during the COVID-19 lockdown (2021)
  93. Attention induced trading and returns: Evidence from robinhood users (2021)
  94. Information acquisition and under-diversification (2010)
  95. Skewness preference and market anomalies (2019)
  96. Equilibrium underdiversification and the preference for skewness (2007)
  97. The rate of communication (2021)
  98. Optimal beliefs, asset prices, and the preference for skewed returns (2007)
  99. Optimal expectations (2005)
  100. Stocks as lotteries: The implications of probability weighting for security prices (2008)
  101. Attention, social interaction, and investor attraction to lottery stocks (2021)
  102. Preference for skew in lotteries: Evidence from the laboratory (2009)
  103. The causal impact of media in financial markets (2011)
  104. IQ, trading behavior, and performance (2012)
  105. Investor sentiment and the mean–variance relation (2011)
  106. Investor attention, overconfidence and category learning (2006)
  107. Individual investor trading and stock returns (2008)
  108. Financial attention (2016)
  109. In search of attention (2011)
  110. Measuring investor sentiment with mutual fund flows (2012)
  111. Risk aversion and portfolio choice (2007)
  112. Retail short selling and stock prices (2017)
  113. Equity portfolio diversification (2008)
  114. Who Owns What? A Factor Model for Direct Stock Holding (2021)
  115. Wisdom of crowds: The value of stock opinions transmitted through social media (2014)
  116. Tail risk and asset prices (2014)
  117. The pricing of tail risk and the equity premium: Evidence from international option markets (2020)
  118. Tails, fears, and risk premia (2011)
  119. Short-term market risks implied by weekly options (2017)
  120. Land of addicts? an empirical investigation of habit-based asset pricing models (2009)
  121. A bound on expected stock returns (2020)
  122. An Adversarial Approach to Structural Estimation (2020) — link
  123. Classification and regression by randomForest (2002)
  124. Implied Risk Aversion Smile (2020)
  125. Deep learning (2016)
  126. Searching for activation functions (2017) — link
  127. Backpropagation: theory, architectures, and applications (1995)
  128. Numerical optimization (2006)
  129. Agency conflicts and cash: Estimates from a dynamic model (2014)
  130. Machine learning benchmarks and random forest regression (2004)
  131. Likelihood approximation by numerical integration on sparse grids (2008) — link
  132. Pricing American Options under High-Dimensional Models with Recursive Adaptive Sparse Expectations* (2018) — link
  133. A neural network-based framework for financial model calibration (2019)
  134. Using Adaptive Sparse Grids to Solve High-Dimensional Dynamic Models (2017) — link
  135. Estimation of Dynamic Discrete Choice Models Using Artificial Neural Network Approximations (2012) — link
  136. What is the Expected Return on a Stock? (2019)
  137. Wealth fluctuations and risk preferences: Evidence from US investor portfolios (2020)
  138. Generalized Bounds on the Conditional Expected Excess Return on Individual Stocks (2020)
  139. Deep Learning in Asset Pricing
  140. Fear trading (2015)
  141. Five facts about beliefs and portfolios (2019)
  142. Multilayer feedforward networks are universal approximators (1989)
  143. Empirical asset pricing via machine learning (2018)
  144. Approximation capabilities of multilayer feedforward networks (1991)
  145. Theory of rational option pricing (1973)
  146. On justifications for the ad hoc Black-Scholes method of option pricing (2009)
  147. Jumps and stochastic volatility: Exchange rate processes implicit in deutsche mark options (1996)
  148. Pricing european-style options under jump diffusion processes with stochastic volatility: Applications of fourier transform (2003)
  149. A closed-form solution for options with stochastic volatility with applications to bond and currency options (1993)
  150. Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification (2018) — link
  151. Gaussian processes with built-in dimensionality reduction: Applications to high-dimensional uncertainty propagation (2016)
  152. Multi-output local Gaussian process regression: Applications to uncertainty quantification (2012)
  153. Multi-output separable Gaussian process: Towards an efficient, fully Bayesian paradigm for uncertainty quantification (2013)
  154. Uncertainty propagation using infinite mixture of Gaussian processes and variational Bayesian inference (2015)
  155. Multidimensional adaptive relevance vector machines for uncertainty quantification (2012)
  156. Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification (2018)
  157. A neural network-based framework for financial model calibration (2019)
  158. Universal approximation using radial-basis-function networks (1991)
  159. Gaussian processes for machine learning (2006)
  160. The Price of the Smile and Variance Risk Premia (2015) — link
  161. Chapter 11 - Macroeconomics and Household Heterogeneity (2016) — link
  162. The Pricing of Options and Corporate Liabilities (1973) — link
  163. Swish: a Self-Gated Activation Function (2017)
  164. New Error Bounds for Deep ReLU Networks Using Sparse Grids (2019) — link
  165. Interest Rate Modeling (2010)
  166. An Adversarial Approach to Structural Estimation (2020) — link
  167. Jumps in equilibrium prices and market microstructure noise (2012) — link
  168. Jumps in High-Frequency Data: Spurious Detections, Dynamics, and News (2016) — link
  169. Telling from Discrete Data Whether the Underlying Continuous-Time Model Is a Diffusion (2002) — link
  170. Pricing American Options under High-Dimensional Models with Recursive Adaptive Sparse Expectations (2018) — link
  171. Machine Learning Projection Methods For Macro-Finance Models (2018) — link
  172. Financial Frictions and the Wealth Distribution (2019) — link
  173. Computing equilibria in dynamic models with occasionally binding constraints (2014) — link
  174. The rebuilding macroeconomic theory project: an analytical assessment (2018) — link
  175. Rethinking large-scale Economic Modeling for Efficiency: Optimizations for GPU and Xeon Phi Clusters (2018) — link
  176. Machine learning for dynamic incentive problems (2018) — link
  177. Solving High-Dimensional Dynamic Portfolio Choice Models with Hierarchical B-Splines on Sparse Grids (2019) — link
  178. The Social Cost of Carbon with Economic and Climate Risks (0) — link
  179. Deep optimal stopping (2018) — link
  180. Parametric Inference and Dynamic State Recovery From Option Panels (2015) — link
  181. The importance of the loss function in option valuation (2004) — link
  182. Structural models of credit risk are useful: Evidence from hedge ratios on corporate bonds (2008) — link
  183. Machine Learning for Continuous-Time Economics (2018) — link
  184. Gradient-Based Structural Estimation (2019)
  185. A nonparametric approach to pricing and hedging derivative securities via learning networks (1994)
  186. Implied Risk Aversion Smile (2020)
  187. Comparing Solution Methodologies for Macro-Finance Models with Nonlinear Dynamics (2017) — link
  188. Parallelized Dimensional Decomposition for Large-Scale Dynamic Stochastic Economic Models (2017) — link
  189. Using Adaptive Sparse Grids to Solve High-Dimensional Dynamic Models (2017) — link
  190. Deep hedging (2019) — link
  191. Machine learning projection methods for macro-finance models (2019)
  192. Pattern Recognition and Machine Learning (Information Science and Statistics) (2006)
  193. A Comprehensive Look at The Empirical Performance of Equity Premium Prediction (2007) — link
  194. Deep Equilibrium Nets (2019) — link
  195. Large-scale Sparse Inverse Covariance Matrix Estimation (2019) — link
  196. Do retail trades move markets? (2008)
  197. Are retail traders compensated for providing liquidity? (2016)
  198. Optimal Taxation without State-Contingent Debt (2002) — link
  199. Will Artificial Intelligence Replace Computational Economists Any Time Soon? (2019) — link
  200. Machine learning for high-dimensional dynamic stochastic economies (2019) — link
  201. Active Subspaces: Emerging Ideas for Dimension Reduction in Parameter Studies (2015)
  202. Projection methods for solving aggregate growth models (1992) — link
  203. Smolyak method for solving dynamic economic models: Lagrange interpolation, anisotropic grid and adaptive domain (2014) — link
  204. Efficient Estimation of Models with Conditional Moment Restrictions Containing Unknown Functions (2003) — link
  205. Improved rates and asymptotic normality for nonparametric neural network estimators (1999)
  206. Chapter 76 Large Sample Sieve Estimation of Semi-Nonparametric Models (2007) — link
  207. Transform Analysis and Asset Pricing for Affine Jump-diffusions (2000) — link
  208. Tails, Fears, and Risk Premia (2011) — link
  209. Artificial intelligence as structural estimation: Deep Blue, Bonanza, and AlphaGo (2020) — link
  210. Machine learning and structural econometrics: contrasts and synergies (2020) — link
  211. Parametric inference and dynamic state recovery from option panels (2015)
  212. Using MPI (1999)
  213. Recursive Methods in Economic Dynamics (1989)
  214. High Dimensional Model Representations (2001) — link
  215. Generalized Functional ANOVA Diagnostics for High-Dimensional Functions of Dependent Variables (2007) — link
  216. Anchor Points Matter in ANOVA Decomposition (2011) — link
  217. On the rationale of maximum-entropy methods (1982) — link
  218. Numerical Methods in Economics (1998)
  219. Comparison of solutions to the multi-country Real Business Cycle model (2011) — link
  220. Option pricing with a direct adaptive sparse grid approach (2012) — link
  221. High-performance computing systems: Status and outlook (2012) — link
  222. A first course in cryptanalysis (1943)
  223. A Generalized ANOVA Dimensional Decomposition for Dependent Probability Measures (2014) — link
  224. A multigrid algorithm for higher order finite elements on sparse grids (1997) — link
  225. a Note on the Construction of \ L \ -Fold Sparse Tensor Product Spaces (2013)
  226. A univariate dimension-reduction method for multi-dimensional integration in stochastic mechanics (2004) — link
  227. Adaptive ANOVA decomposition of stochastic incompressible and compressible flows (2012) — link
  228. Adaptive Control Processes: A Guided Tour (1961)
  229. On the consequences of demographic change for rates of returns to capital, and the distribution of wealth and welfare (2007) — link
  230. Computing Equilibria in Dynamic Stochastic Macro-Models with Heterogeneous Agents (2017)
  231. The Role of Immigration in Dealing with the Developed World’s Demographic Transition (2004) — link
  232. Algorithm 847 : spinterp : Piecewise Multilinear Hierarchical Sparse Grid Interpolation in M ATLAB (2005) — link
  233. An adaptive high-dimensional stochastic model representation technique for the solution of stochastic partial differential equations (2010) — link
  234. An Efficient Computational Framework for Uncertainty Quantification in Multiscale Systems (2010)
  235. Bachelier, Louis (1870–1946) (1946)
  236. Chapt ’ Er
  237. Compact Data Structure and Scalable (2011) — link
  238. Ageing, Pension Reform and Capital Flows: A Multi-Country Simulation Model (2006) — link
  239. Compact data structure and scalable algorithms for the sparse grid technique (2011) — link
  240. Comparison of solutions to the multi-country Real Business Cycle model (2011) — link
  241. Convex Optimization (2010) — link
  242. Dimensions, Embeddings, and Attractors (2010) — link
  243. DSGE-CH: A dynamic stochastic general equilibrium model for Switzerland (2009) — link
  244. Dynamic programming. (2014) — link
  245. Econometrics (2000)
  246. Evolutionary Algorithms for Solving Multi-Objective Problems Second Edition (2007) — link
  247. General formulation of HDMR component functions with independent and correlated variables (2012) — link
  248. Generalized Functional ANOVA Diagnostics for High-Dimensional Functions of Dependent Variables (2007) — link
  249. High dimensional model representation for stochastic finite element analysis (2010) — link
  250. High Dimensional Polynomial Interpolation On Sparse Grids (1999)
  251. High dimensional polynomial interpolation on sparse grids (2000) — link
  252. High Performance Parallelism Pearls: Multicore and Many-core Programming Approaches (2015) — link
  253. How to Solve Dynamic Stochastic Models Computing Expectations Just Once (2011) — link
  254. Intel threading building blocks : outfitting C++ for multi-core processor parallelism (2007)
  255. Introduction to ARCH & GARCH models (2001)
  256. Introduction to Statistics (1997) — link
  257. Lecture Notes in Computational Science and Engineering: Preface (2008) — link
  258. Macroeconomic theory (1981) — link
  259. Matrix Computations (2013)
  260. A sparse grid stochastic collocation method for partial differential equations with random input data (2008) — link
  261. Multi-objective evolutionary algorithms for energy-efficiency in heterogeneous wireless sensor networks (2014) — link
  262. Multiplying matrices in O(n (2014)
  263. Multiscale modeling and simulation in science (2009)
  264. Multivariate Quadrature on Adaptive Sparse Grids (2003) — link
  265. Nonlinear Dynamics and Chaos (1994) — link
  266. Numerical Integration using Sparse Grids (1998) — link
  267. Numerical Methods in Economics (1998) — link
  268. Numerical methods in economics (1998)
  269. On decompositions of multivariate functions (2009) — link
  270. ON DECOMPOSITIONS OF MULTIVARIATE FUNCTIONS (2010)
  271. On the approximation error in high dimensional model representation (2008) — link
  272. On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming (2005) — link
  273. ORNL REPORT User Manual : TASMANIAN Sparse Grids v3 . 0 (2015)
  274. Orthogonality Relations
  275. Some advances on anchored anova expansion for high order moments computation (2014)
  276. Sparse Grid Methods for Higher Dimensional Approximation (2010) — link
  277. Sparse Grid Quadrature — link
  278. Sparse Grid Quadrature in High Dimensions with Applications in Finance and Insurance (2010) — link
  279. Nonlinear Interpolation of Multivariable Functions by the Monte Carlo Method (1970) — link
  280. Merging simulation and projection approaches to solve high-dimensional problems with an application to a new K eynesian model (2015) — link
  281. Nonlinear adventures at the zero lower bound (2015) — link
  282. Sparse grids (2004) — link
  283. Sparse Grids and Applications (2012) — link
  284. Sparse grids and applications (2013) — link
  285. Sparse Grids and High Dimensional Model Representation – a Comparison (2014)
  286. Spatially adaptive sparse grids for high-dimensional data-driven problems (2010) — link
  287. Estimating DSGE Models: Recent Advances and Future Challenges (2020) — link
  288. Deep Neural Networks for Estimation and Inference (2021) — link
  289. Efficient cosmological parameter sampling using sparse grids (2010)
  290. Spectral Methods for Time-Dependent Problems
  291. Spectral Methods Fundamentals in Single Domains (2006) — link
  292. Sparse Grids in a Nutshell (2013) — link
  293. Spectral Methods in Matlab (2000) — link
  294. Springer Finance (2008) — link
  295. Table of of contents (1940) — link
  296. Theorems and examples on high dimensional model representation (2003) — link
  297. Using MPI : portable parallel programming with the Message-Passing-Interface
  298. [Richard _ Bellman] _ Dynamic _ Programming(BookZZ.org).pdf
  299. ¨ F Ur ¨ Informatik Fakult At ¨ (2016)
  300. Local and Dimension Adaptive Stochastic Collocation for Uncertainty Quantification (2013) — link
  301. Dynare: Reference Manual Version 4 (2018) — link
  302. Solving High-Dimensional Dynamic Programming Problems using Deep Learning (2020) — link
  303. Adaptive sparse grids (2003) — link
  304. Monetary policy according to HANK (2018)
  305. Global wealth inequality (2019)
  306. Computing equilibrium in OLG models with stochastic production (2004) — link
  307. Limited asset markets participation, monetary policy and (inverted) aggregate demand logic (2008)
  308. Financial Frictions and the Wealth Distribution (2019) — link
  309. Wealth Inequality in the United States since 1913: Evidence from Capitalized Income Tax Data * (2016) — link
  310. Cross-sectional facts for macroeconomists (2010) — link
  311. Monetary policy with heterogeneous agents: Insights from TANK models (2017)
  312. An Adaptive Wavelet Stochastic Collocation Method for Irregular Solutions of Partial differential Equations with Random Input Data (2014) — link
  313. A stochastic collocation method for elliptic partial differential equations with random input data (2007) — link
  314. Stationary Equilibria in Asset-Pricing Models with Incomplete Markets and Collateral (2003) — link
  315. Making Carbon Taxation a Generational Win Win (2019) — link
  316. A surrogate model for computational homogenization of elastostatics at finite strain using high-dimensional model representation-based neural network (2020) — link
  317. A sparse grid based method for generative dimensionality reduction of high-dimensional data (2016) — link
  318. Post-‘87 crash fears in the S&P 500 futures option market (2000) — link
  319. The jump-risk premia implicit in options: evidence from an integrated time-series study (2002) — link
  320. Random Forests (2001)
  321. Approximation, perturbation, and projection methods in economic analysis (1996) — link
  322. Large Sample Properties of Generalized Method of Moments Estimators (1982)
  323. Demand for Crash Insurance, Intermediary Constraints, and Risk Premia in Financial Markets (2019)
  324. When Leverage Ratio Meets Derivatives: Running Out Of Options? (2019)
  325. The curious case of neural text degeneration (2019)
  326. Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models (2018) — link
  327. Language to logical form with neural attention (2016) — link
  328. Stochastic Beam Search for Neural Machine Translation (2019) — link
  329. Sequence Level Training with Recurrent Neural Networks (2016) — link
  330. The Llama 3 Herd of Models (2024)
  331. Are llms capable of data-based statistical and causal reasoning? benchmarking advanced quantitative reasoning with data (2024) — link
  332. Sequence to Sequence Learning with Neural Networks (2014)
  333. Hierarchical Neural Story Generation (2018)
  334. Language models are few-shot learners (2020)
  335. Training compute-optimal large language models (2022) — link
  336. Adaptive Mixture of Local Experts (1991)
  337. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models (2024) — link
  338. Bias and Fairness in Large Language Models: A Survey (2024)
  339. The changing economics of knowledge production (2024)
  340. Does Generative AI Facilitate Investor Trading? Evidence from ChatGPT Outages (2024)
  341. Probabilistic transformers (2020)
  342. Efficient Large Scale Language Modeling with Mixtures of Experts (2022)
  343. A Closer Look into Mixture-of-Experts in Large Language Models (2024)
  344. From cashews to nudges: The evolution of behavioral economics (2018)
  345. Rational expectations and the theory of price movements (1961)
  346. Caution Ahead: Numerical Reasoning and Look-ahead Bias in AI Models (2024)
  347. Can chatgpt forecast stock price movements? return predictability and large language models (2023)
  348. Financial statement analysis with large language models — → 2407.17866
  349. AI in Finance and Information Overload (2025)
  350. Generative AI and asset management (2024)
  351. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 (2024) — link
  352. Attention Is All You Need (2017) — link
  353. Language Models are Unsupervised Multitask Learners (2019)
  354. GPT-4 Technical Report (2024) — link
  355. Gemini: A Family of Highly Capable Multimodal Models (2025) — link
  356. The Llama 3 Herd of Models (2024) — link
  357. An overview of gradient descent optimization algorithms (2017) — link

3 of 365 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.