Responsible LLM Deployment for High-Stake Decisions by Decentralized Technologies and Human-AI Interactions ArXiv ID: 2512.04108 “View on arXiv” Authors: Swati Sachan, Theo Miller, Mai Phuong Nguyen Abstract High-stakes decision domains are increasingly exploring the potential of Large Language Models (LLMs) for complex decision-making tasks. However, LLM deployment in real-world settings presents challenges in data security, evaluation of its capabilities outside controlled environments, and accountability attribution in the event of adversarial decisions. This paper proposes a framework for responsible deployment of LLM-based decision-support systems through active human involvement. It integrates interactive collaboration between human experts and developers through multiple iterations at the pre-deployment stage to assess the uncertain samples and judge the stability of the explanation provided by post-hoc XAI techniques. Local LLM deployment within organizations and decentralized technologies, such as Blockchain and IPFS, are proposed to create immutable records of LLM activities for automated auditing to enhance security and trace back accountability. It was tested on Bert-large-uncased, Mistral, and LLaMA 2 and 3 models to assess the capability to support responsible financial decisions on business lending. ...

Signature approach for pricing and hedging path-dependent options with frictions ArXiv ID: 2511.23295 “View on arXiv” Authors: Eduardo Abi Jaber, Donatien Hainaut, Edouard Motte Abstract We introduce a novel signature approach for pricing and hedging path-dependent options with instantaneous and permanent market impact under a mean-quadratic variation criterion. Leveraging the expressive power of signatures, we recast an inherently nonlinear and non-Markovian stochastic control problem into a tractable form, yielding hedging strategies in (possibly infinite) linear feedback form in the time-augmented signature of the control variables, with coefficients characterized by non-standard infinite-dimensional Riccati equations on the extended tensor algebra. Numerical experiments demonstrate the effectiveness of these signature-based strategies for pricing and hedging general path-dependent payoffs in the presence of frictions. In particular, market impact naturally smooths optimal trading strategies, making low-truncated signature approximations highly accurate and robust in frictional markets, contrary to the frictionless case. ...

Adaptive Dueling Double Deep Q-networks in Uniswap V3 Replication and Extension with Mamba ArXiv ID: 2511.22101 “View on arXiv” Authors: Zhaofeng Zhang Abstract The report goes through the main steps of replicating and improving the article “Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning.” The replication part includes how to obtain data from the Uniswap Subgraph, details of the implementation, and comments on the results. After the replication, I propose a new structure based on the original model, which combines Mamba with DDQN and a new reward function. In this new structure, I clean the data again and introduce two new baselines for comparison. As a result, although the model has not yet been applied to all datasets, it shows stronger theoretical support than the original model and performs better in some tests. ...

Beta-Dependent Gamma Feedback and Endogenous Volatility Amplification in Option Markets ArXiv ID: 2511.22766 “View on arXiv” Authors: Haoying Dai Abstract We develop a theoretical framework that aims to link micro-level option hedging and stock-specific factor exposure with macro-level market turbulence and explain endogenous volatility amplification during gamma-squeeze events. By explicitly modeling market-maker delta-neutral hedging and incorporating beta-dependent volatility normalization, we derive a stability condition that characterizes the onset of a gamma-squeeze event. The model captures a nonlinear recursive feedback loop between market-maker hedging and price movements and the resulting self-reinforcing dynamics. From a complex-systems perspective, the dynamics represent a bounded nonlinear response in which effective gain depends jointly on beta-normalized shock perception and gamma-scaled sensitivity. Our analysis highlights that low-beta stocks exhibit disproportionately strong feedback even for modest absolute price movements. ...

Factors Influencing Cryptocurrency Prices: Evidence from Bitcoin, Ethereum, Dash, Litecoin, and Monero ArXiv ID: 2511.22782 “View on arXiv” Authors: Yhlas Sovbetov Abstract This paper examines factors that influence prices of most common five cryptocurrencies such as Bitcoin, Ethereum, Dash, Litecoin, and Monero over 2010-2018 using weekly data. The study employs ARDL technique and documents several findings. First, cryptomarket-related factors such as market beta, trading volume, and volatility appear to be significant determinant for all five cryptocurrencies both in short- and long-run. Second, attractiveness of cryptocurrencies also matters in terms of their price determination, but only in long-run. This indicates that formation (recognition) of the attractiveness of cryptocurrencies are subjected to time factor. In other words, it travels slowly within the market. Third, SP500 index seems to have weak positive long-run impact on Bitcoin, Ethereum, and Litcoin, while its sign turns to negative losing significance in short-run, except Bitcoin that generates an estimate of -0.20 at 10% significance level. Lastly, error-correction models for Bitcoin, Etherem, Dash, Litcoin, and Monero show that cointegrated series cannot drift too far apart, and converge to a long-run equilibrium at a speed of 23.68%, 12.76%, 10.20%, 22.91%, and 14.27% respectively. ...

Black-Litterman and ESG Portfolio Optimization ArXiv ID: 2511.21850 “View on arXiv” Authors: Aviv Alpern, Svetlozar Rachev Abstract We introduce a simple portfolio optimization strategy using ESG data with the Black-Litterman allocation framework. ESG scores are used as a bias for Stein shrinkage estimation of equilibrium risk premiums used in assigning Black-Litterman asset weights. Assets are modeled as multivariate affine normal-inverse Gaussian variables using CVaR as a risk measure. This strategy, though very simple, when employed with a soft turnover constraint is exceptionally successful. Portfolios are reallocated daily over a 4.7 year period, each with a different set of hyperparameters used for optimization. The most successful strategies have returns of approximately 40-45% annually. ...

Informative Risk Measures in the Banking Industry: A Proposal based on the Magnitude-Propensity Approach ArXiv ID: 2511.21556 “View on arXiv” Authors: Michele Bonollo, Martino Grasselli, Gianmarco Mori, Havva Nilsu Oz Abstract Despite decades of research in risk management, most of the literature has focused on scalar risk measures (like e.g. Value-at-Risk and Expected Shortfall). While such scalar measures provide compact and tractable summaries, they provide a poor informative value as they miss the intrinsic multivariate nature of risk.To contribute to a paradigmatic enhancement, and building on recent theoretical work by Faugeras and Pagés (2024), we propose a novel multivariate representation of risk that better reflects the structure of potential portfolio losses, while maintaining desirable properties of interpretability and analytical coherence. The proposed framework extends the classical frequency-severity approach and provides a more comprehensive characterization of extreme events. Several empirical applications based on real-world data demonstrate the feasibility, robustness and practical relevance of the methodology, suggesting its potential for both regulatory and managerial applications. ...

Integrating LSTM Networks with Neural Levy Processes for Financial Forecasting ArXiv ID: 2512.07860 “View on arXiv” Authors: Mohammed Alruqimi, Luca Di Persio Abstract This paper investigates an optimal integration of deep learning with financial models for robust asset price forecasting. Specifically, we developed a hybrid framework combining a Long Short-Term Memory (LSTM) network with the Merton-Lévy jump-diffusion model. To optimise this framework, we employed the Grey Wolf Optimizer (GWO) for the LSTM hyperparameter tuning, and we explored three calibration methods for the Merton-Levy model parameters: Artificial Neural Networks (ANNs), the Marine Predators Algorithm (MPA), and the PyTorch-based TorchSDE library. To evaluate the predictive performance of our hybrid model, we compared it against several benchmark models, including a standard LSTM and an LSTM combined with the Fractional Heston model. This evaluation used three real-world financial datasets: Brent oil prices, the STOXX 600 index, and the IT40 index. Performance was assessed using standard metrics, including Mean Squared Error (MSE), Mean Absolute Error(MAE), Mean Squared Percentage Error (MSPE), and the coefficient of determination (R2). Our experimental results demonstrate that the hybrid model, combining a GWO-optimized LSTM network with the Levy-Merton Jump-Diffusion model calibrated using an ANN, outperformed the base LSTM model and all other models developed in this study. ...

Portfolio Optimization via Transfer Learning ArXiv ID: 2511.21221 “View on arXiv” Authors: Kexin Wang, Xiaomeng Zhang, Xinyu Zhang Abstract Recognizing that asset markets generally exhibit shared informational characteristics, we develop a portfolio strategy based on transfer learning that leverages cross-market information to enhance the investment performance in the market of interest by forward validation. Our strategy asymptotically identifies and utilizes the informative datasets, selectively incorporating valid information while discarding the misleading information. This enables our strategy to achieve the maximum Sharpe ratio asymptotically. The promising performance is demonstrated by numerical studies and case studies of two portfolios: one consisting of stocks dual-listed in A-shares and H-shares, and another comprising equities from various industries of the United States. ...

Constrained deep learning for pricing and hedging european options in incomplete markets ArXiv ID: 2511.20837 “View on arXiv” Authors: Nicolas Baradel Abstract In incomplete financial markets, pricing and hedging European options lack a unique no-arbitrage solution due to unhedgeable risks. This paper introduces a constrained deep learning approach to determine option prices and hedging strategies that minimize the Profit and Loss (P&L) distribution around zero. We employ a single neural network to represent the option price function, with its gradient serving as the hedging strategy, optimized via a loss function enforcing the self-financing portfolio condition. A key challenge arises from the non-smooth nature of option payoffs (e.g., vanilla calls are non-differentiable at-the-money, while digital options are discontinuous), which conflicts with the inherent smoothness of standard neural networks. To address this, we compare unconstrained networks against constrained architectures that explicitly embed the terminal payoff condition, drawing inspiration from PDE-solving techniques. Our framework assumes two tradable assets: the underlying and a liquid call option capturing volatility dynamics. Numerical experiments evaluate the method on simple options with varying non-smoothness, the exotic Equinox option, and scenarios with market jumps for robustness. Results demonstrate superior P&L distributions, highlighting the efficacy of constrained networks in handling realistic payoffs. This work advances machine learning applications in quantitative finance by integrating boundary constraints, offering a practical tool for pricing and hedging in incomplete markets. ...