64 papers
Debiasing LLMs by Fine-tuning
Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We propose a supervised fine-tuning (SFT) approach that uses Low-Rank Adaptation (LoRA) to train off-the-shelf LLMs on instruction datasets constructed from rational benchmark forecasts. By intervening at the parameter level, SFT changes how LLMs map observed information into forecasts and thereby mitigates extrapolation bias. We evaluate the fine-tuned model in two settings: controlled forecasting experiments and cross-sectional stock return prediction. In both settings, fine-tuning corrects the extrapolative bias out-of-sample, establishing a low-cost and generalizable method for debiasing LLMs.
2604.02921Apr 2026
View
2603.22880Portfolio Optimization under Recursive Utility via Reinforcement Learning
We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility involves a certainty equivalent (CE) of future value that has no closed form under observed returns; we approximate it by $K$-sample Monte Carlo and train actor-critic (PPO, A2C) on the resulting value target and an approximate advantage estimate (AAE) that generalizes the Bellman residual to multi-step with state-dependent weights. This formulation applies only to critic-based algorithms. On 10 chronological train/test splits of South Korean ETF data, the recursive-utility agent improves on the discounted (naive) baseline in Sharpe ratio, max drawdown, and cumulative return. Derivations, world model and metrics, and full result tables are in the appendices.
2603.22880Mar 2026
View
Financial Dynamics and Interconnected Risk of Liquid Restaking
Decentralized finance introduces new business models and use cases as part of digital finance. Restaking has recently emerged as a transformative mechanism in DeFi, promising extra yields but introducing complex and interconnected risks. The paper monitors the current restaking landscape, empirically analyzes the revenue drivers of a liquid restaking protocol, and conducts a technical investigation on the emitted risk arising from the interconnection between liquid restaking and other protocols. The revenue dynamics of Renzo Protocol are analyzed by employing an OLS regression model, Granger-causality and random forest feature importance tests. Our results identify that revenue is primarily predicted by the value locked in the underlying EigenLayer ecosystem, the yield of Renzo protocol's liquid restaking token and the multi-blockchain expansion of that token. The multi-blockchain expansion of the liquid restaking token presents a double-edged sword: bridging to other networks is crucial for user adoption, but it adds the bridge risks to the existing risks of restaking. We investigate the cross-contamination risk between different DeFi services and the liquid restaking protocol. By mapping the asset flow across the decentralized finance ecosystem, it is detected that the bridge risk of the current size of Renzo's liquid-restaking assets does not impose a systemic risk on the current restaking and staking ecosystem. To address the potential consequences of the emphasized interconnection risks, we introduce two hypothetical scenarios and a stress test, assuming a large number of compromised liquid restaking tokens and a smart contract logic failure in a DeFi protocol. Considering the overall liquid-restaking protocols and the growing interconnection, this analysis requires further work to explore the growing complexities.
2604.03274Mar 2026
View2604.00031Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex Trading
Applying reinforcement learning (RL) to foreign exchange (Forex) trading remains challenging because realistic environments, well-defined reward functions, and expressive action spaces must be satisfied simultaneously, yet many prior studies rely on simplified simulators, single scalar rewards, and restricted action representations, limiting both interpretability and practical relevance. This paper presents a modular RL framework designed to address these limitations through three tightly integrated components: a friction-aware execution engine that enforces strict anti-lookahead semantics, with observations at time t, execution at time t+1, and mark-to-market at time t+1, while incorporating realistic costs such as spread, commission, slippage, rollover financing, and margin-triggered liquidation; a decomposable 11-component reward architecture with fixed weights and per-step diagnostic logging to enable systematic ablation and component-level attribution; and a 10-action discrete interface with legal-action masking that encodes explicit trading primitives while enforcing margin-aware feasibility constraints. Empirical evaluation on EURUSD focuses on learning dynamics rather than generalization and reveals strongly non-monotonic reward interactions, where additional penalties do not reliably improve outcomes; the full reward configuration achieves the highest training Sharpe (0.765) and cumulative return (57.09 percent). The expanded action space increases return but also turnover and reduces Sharpe relative to a conservative 3-action baseline, indicating a return-activity trade-off under a fixed training budget, while scaling-enabled variants consistently reduce drawdown, with the combined configuration achieving the strongest endpoint performance.
2604.00031Mar 2026
View
LR-Robot: A Unified Supervised Intelligent Framework for Real-Time Systematic Literature Reviews with Large Language Models
Recent advances in artificial intelligence (AI) and natural language processing (NLP) have enabled tools to support systematic literature reviews (SLRs), yet existing frameworks often produce outputs that are efficient but contextually limited, requiring substantial expert oversight.The framework employs a human-in-the-loop process to define sub-SLR tasks, evaluate models, and ensure methodological rigor, while leveraging structured knowledge sources and retrieval-augmented generation (RAG) to enhance factual grounding and transparency. LR-Robot enables multidimensional categorization of research, maps relationships among papers, identifies high-impact works, and supports historical, fine-grained analyses of topic evolution. We demonstrate the framework using an option pricing case study, enabling comprehensive literature analysis. Empirical results reveal the current capabilities of AI in understanding and synthesizing literature, uncover emerging trends, reveal topic connections, and highlight core research directions. By accelerating labor-intensive review stages while preserving interpretive accuracy, LR-Robot provides a practical, customizable, and high-quality approach for AI-assisted SLRs. Key contributions: (1) a novel framework combining AI and expert supervision for contextually informed SLRs, (2) support for multidimensional categorization, relationship mapping, and fine-grained topic evolution analysis, and (3) empirical demonstration of AI-driven literature synthesis in the field of option pricing.
2603.17723Mar 2026
View2603.14491Private Credit Markets Theory, Evidence, and Emerging Frontiers
Private credit assets under management grew from \$158 billion in 2010 to nearly \$2 trillion globally by mid-2024, fundamentally reshaping corporate credit markets. This paper provides a systematic survey of the academic literature on private credit, organizing theory and evidence around four questions: why the market has grown so rapidly, how direct lender technology differs from bank lending, what risk-adjusted returns investors earn, and whether the sector poses systemic risks. We develop an integrated theoretical framework linking delegated monitoring, soft-information processing, and incomplete contracting to the institutional specifics of modern direct lending. The empirical evidence documents a distinctive lending technology serving opaque, private-equity-sponsored borrowers at a meaningful and persistent spread premium over the broadly syndicated loan market, while performance evidence suggests that risk-adjusted returns for the average fund are largely consumed by fees.
2603.14491Mar 2026
View2603.13942AI Agents in Financial Markets: Architecture, Applications, and Systemic Implications
Recent advances in large language models, tool-using agents, and financial machine learning are shifting financial automation from isolated prediction tasks to integrated decision systems that can perceive information, reason over objectives, and generate or execute actions. This paper develops an integrative framework for analysing agentic finance: financial market environments in which autonomous or semi-autonomous AI systems participate in information processing, decision support, monitoring, and execution workflows. The analysis proceeds in three steps. First, the paper proposes a four-layer architecture of financial AI agents covering data perception, reasoning engines, strategy generation, and execution with control. Second, it introduces the Agentic Financial Market Model (AFMM), a stylised agent-based representation linking agent design parameters such as autonomy depth, heterogeneity, execution coupling, infrastructure concentration, and supervisory observability to market-level outcomes including efficiency, liquidity resilience, volatility, and systemic risk. Third, it develops an illustrative empirical application based on event studies of AI-agent capability disclosures and heterogeneous market repricing. The central argument is that the systemic implications of AI in finance depend less on model intelligence alone than on how agent architectures are distributed, coupled, and governed across institutions. In the near term, the most plausible equilibrium is bounded autonomy, in which AI agents operate as supervised co-pilots, monitoring systems, and constrained execution modules embedded within human decision processes.
2603.13942Mar 2026
View
When David becomes Goliath: Repo dealer-driven bond mispricing
This paper studies the impact of funding market frictions on bond prices and market-wide liquidity. Using proprietary transaction-level data on all gilt-backed repo and reverse-repo trades, we demonstrate how the market power of individual dealers and their linkages generate frictions. Specifically, we show that frictions related to market power account for between 0.5 and 1.3 percentage points of bond yield deviation, while the transmission of heterogeneously persistent shocks between dealers accounts for between 2 and 4 percentage points of yield deviation.
2603.10690Mar 2026
View
From debt crises to financial crashes (and back): a stock-flow consistent model for stock price bubbles
We develop a stochastic macro-financial model in continuous time by integrating two specifications of the Keen economic framework with a financial market driven by a jump-diffusion process. The economic block of the model combines monetary debt-deflation mechanisms with Ponzi-type financial destabilization and is influenced by the financial market through a stochastic interest rate that depends on asset price returns. The financial market block of the model consists of an asset with jump--diffusion price process with endogenous, state-dependent jump intensities driven by speculative credit flows. The model formalizes a feedback loop linking credit expansion, crash risk, perceived return dynamics, and bank lending spreads. Under suitable parameter restrictions, we establish global existence and non-explosion of the coupled system. Numerical experiments illustrate how variations in credit sensitivity and jump parameters generate regimes ranging from stable growth to recurrent boom--bust cycles. The framework provides a tractable setting for analyzing endogenous financial fragility within a mathematically well-posed macro--financial system.
2603.07213Mar 2026
View
Impacts of Economic Policies on Wealth Distribution in Token Economies
In this paper, we analyse the impacts of exogenous and endogenous factors on wealth distribution in the Bitcoin token economy, where wealth distribution refers to the distribution of BTC between economic participants or groups of economic participants. The objective of the paper is to analyse the impact of economic policies on wealth distribution in the Bitcoin ecosystem. Different macroeconomic and microeconomic time series are used to eliminate noise in the wealth distribution time series, and the causality analysis is performed between Bitcoin Improvement Proposals (i.e., BIPs) and the cleaned wealth distribution data to reveal possible patterns in the impacts that the endogenous policies have on wealth distribution in token economies. Lastly, a structure for economic policy taxonomy in token economies is proposed where different the policy implementations are illustrated by existing BIPs. This approach highlights the actions available to the policy makers, as well as providing a technique for analysis of policy impacts in token economies and their categorization.
2602.17373Feb 2026
View
Market Efficiency and the Heterogeneous Impact of Financial Liberalization: Evidence from the Shanghai-Hong Kong Stock Connect
This paper investigates the impact of the Shanghai-Hong Kong Stock Connect (SHHK Stock Connect) on the A-H share price premium and examines whether the policy effect is contingent on market efficiency. Using monthly data for 67 Shanghai-listed A-H dual-listed firms from January 2011 to May 2019, we employ a dynamic panel model estimated via two-step system generalized method of moment (GMM) to account for the persistence of the premium and potential endogeneity. Market efficiency is proxied by trading-friction measures derived from daily high-low price ranges. Our findings indicate that the implementation of SHHK Stock Connect is associated with an average 18.4% increase in the A-H premium. However, this effect is heterogeneous: the marginal impact of the policy is more pronounced for firms operating in less efficient markets and weaker for those with higher efficiency, suggesting that pre-existing trading frictions shape the policy outcome. No significant response is observed at the announcement stage. Placebo tests and alternative efficiency measures confirm the robustness of the efficiency-dependent effect. Overall, the results underscore the importance of the information environment in shaping the outcomes of financial liberalization.
2602.14754Feb 2026
View
Seeing the Goal, Missing the Truth: Human Accountability for AI Bias
This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock returns or earnings) of LLM outputs leads the LLM to generate biased sentiment and competition measures, even though these measures are intended to be downstream task-independent. Goal-aware prompting shifts intermediate measures toward the disclosed downstream objective. This purpose leakage improves performance before the LLM's knowledge cutoff, but with no advantage post-cutoff. AI bias due to "seeing the goal" is not an algorithmic flaw, but stems from human accountability in research design to ensure the statistical validity and reliability of AI-generated measurements.
2602.09504Feb 2026
View
Forecasting Future Language: Context Design for Mention Markets
Mention markets, a type of prediction market in which contracts resolve based on whether a specified keyword is mentioned during a future public event, require accurate probabilistic forecasts of keyword-mention outcomes. While recent work shows that large language models (LLMs) can generate forecasts competitive with human forecasters, it remains unclear how input context should be designed to support accurate prediction. In this paper, we study this question through experiments on earnings-call mention markets, which require forecasting whether a company will mention a specified keyword during its upcoming call. We run controlled comparisons varying (i) which contextual information is provided (news and/or prior earnings-call transcripts) and (ii) how \textit{market probability}, (i.e., prediction market contract price) is used. We introduce Market-Conditioned Prompting (MCP), which explicitly treats the market-implied probability as a prior and instructs the LLM to update this prior using textual evidence, rather than re-predicting the base rate from scratch. In our experiments, we find three insights: (1) richer context consistently improves forecasting performance; (2) market-conditioned prompting (MCP), which treats the market probability as a prior and updates it using textual evidence, yields better-calibrated forecasts; and (3) a mixture of the market probability and MCP (MixMCP) outperforms the market baseline. By dampening the LLM's posterior update with the market prior, MixMCP yields more robust predictions than either the market or the LLM alone.
2602.21229Feb 2026
View
Beyond Carr Madan: A Projection Approach to Risk-Neutral Moment Estimation
We propose a projection method to estimate risk-neutral moments from option prices. We derive a finite-sample bound implying that the projection estimator attains (up to a constant) the smallest pricing error within the span of traded option payoffs. This finite-sample optimality is not available for the widely used Carr--Madan approximation. Simulations show sizable accuracy gains for key quantities such as VIX and SVIX. We then extend the framework to multiple underlyings, deriving necessary and sufficient conditions under which simple options complete the market in higher dimensions, and providing estimators for joint moments. In our empirical application, we recover risk-neutral correlations and joint tail risk from FX options alone, addressing a longstanding measurement problem raised by Ross (1976). Our joint tail-risk measure predicts future joint currency crashes and identifies periods in which currency portfolios are particularly useful for hedging.
2601.14852Jan 2026
View
Autonomous Market Intelligence: Agentic AI Nowcasting Predicts Stock Returns
Can fully agentic AI nowcast stock returns? We deploy a state-of-the-art Large Language Model to evaluate the attractiveness of each Russell 1000 stock daily, starting from April 2025 when AI web interfaces enabled real-time search. Our data contribution is unique along three dimensions. First, the nowcasting framework is completely out-of-sample and free of look-ahead bias by construction: predictions are collected at the current edge of time, ensuring the AI has no knowledge of future outcomes. Second, this temporal design is irreproducible -- once the information environment passes, it can never be recreated. Third, our framework is 100% agentic: we do not feed the model news, disclosures, or curated text; it autonomously searches the web, filters sources, and synthesises information into quantitative predictions. We find that AI possesses genuine stock selection ability, but only for identifying top winners. Longing the 20 highest-ranked stocks generates a daily Fama-French five-factor plus momentum alpha of 18.4 basis points and an annualised Sharpe ratio of 2.43. Critically, these returns derive from an implementable strategy trading highly liquid Russell 1000 constituents, with transaction costs representing less than 10\% of gross alpha. However, this predictability is highly concentrated: expanding beyond the top tier rapidly dilutes alpha, and bottom-ranked stocks exhibit returns statistically indistinguishable from the market. We hypothesise that this asymmetry reflects online information structure: genuinely positive news generates coherent signals, while negative news is contaminated by strategic corporate obfuscation and social media noise.
2601.11958Jan 2026
View
A Real-Options-Aware Multi-Criteria Framework for Ex-Ante Real Estate Redevelopment Use Selection
A growing share of the existing real estate stock exhibits persistent underperformance that can no longer be explained by cyclical market phases or inadequate maintenance alone. In many cases, technically recoverable assets located in non-marginal contexts fail to generate economic value consistent with the capital immobilized. This condition reflects a structural misalignment between intended use and effective demand rather than episodic market weakness, and calls for a decision framework capable of integrating value, risk, complexity, and irreversibility in strategic use selection. This study proposes a decision-analytic framework for the ex-ante selection of intended use in real estate redevelopment processes. The framework integrates real-options logic on irreversibility and managerial flexibility with a multi-criteria decision-analysis structure, enabling comparative evaluation of expected economic value, market and operational risk, technical and managerial complexity, and time-to-income. By treating redevelopment primarily as a problem of strategic option selection rather than design or financial optimization, the framework operationalizes option value preservation through disciplined ex-ante screening. Illustrative cases demonstrate how this integration of real options reasoning and MCDA reduces over-complexification and misalignment across different asset types and urban contexts.
2601.22166Jan 2026
View
LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets
We introduce LemonadeBench v0.5, a minimal benchmark for evaluating economic intuition, long-term planning, and decision-making under uncertainty in large language models (LLMs) through a simulated lemonade stand business. Models must manage inventory with expiring goods, set prices, choose operating hours, and maximize profit over a 30-day period-tasks that any small business owner faces daily. All models demonstrate meaningful economic agency by achieving profitability, with performance scaling dramatically by sophistication-from basic models earning minimal profits to frontier models capturing 70% of theoretical optimal, a greater than 10x improvement. Yet our decomposition of business efficiency across six dimensions reveals a consistent pattern: models achieve local rather than global optimization, excelling in select areas while exhibiting surprising blind spots elsewhere.
2602.13209Jan 2026
View
UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos
Multimodal large language models are playing an increasingly significant role in empowering the financial domain, however, the challenges they face, such as multimodal and high-density information and cross-modal multi-hop reasoning, go beyond the evaluation scope of existing multimodal benchmarks. To address this gap, we propose UniFinEval, the first unified multimodal benchmark designed for high-information-density financial environments, covering text, images, and videos. UniFinEval systematically constructs five core financial scenarios grounded in real-world financial systems: Financial Statement Auditing, Company Fundamental Reasoning, Industry Trend Insights, Financial Risk Sensing, and Asset Allocation Analysis. We manually construct a high-quality dataset consisting of 3,767 question-answer pairs in both chinese and english and systematically evaluate 10 mainstream MLLMs under Zero-Shot and CoT settings. Results show that Gemini-3-pro-preview achieves the best overall performance, yet still exhibits a substantial gap compared to financial experts. Further error analysis reveals systematic deficiencies in current models. UniFinEval aims to provide a systematic assessment of MLLMs' capabilities in fine-grained, high-information-density financial environments, thereby enhancing the robustness of MLLMs applications in real-world financial scenarios. Data and code are available at https://github.com/aifinlab/UniFinEval.
2601.22162Jan 2026
View
An Algorithmic Framework for Systematic Literature Reviews: A Case Study for Financial Narratives
This paper introduces an algorithmic framework for conducting systematic literature reviews (SLRs), designed to improve efficiency, reproducibility, and selection quality assessment in the literature review process. The proposed method integrates Natural Language Processing (NLP) techniques, clustering algorithms, and interpretability tools to automate and structure the selection and analysis of academic publications. The framework is applied to a case study focused on financial narratives, an emerging area in financial economics that examines how structured accounts of economic events, formed by the convergence of individual interpretations, influence market dynamics and asset prices. Drawing from the Scopus database of peer-reviewed literature, the review highlights research efforts to model financial narratives using various NLP techniques. Results reveal that while advances have been made, the conceptualization of financial narratives remains fragmented, often reduced to sentiment analysis, topic modeling, or their combination, without a unified theoretical framework. The findings underscore the value of more rigorous and dynamic narrative modeling approaches and demonstrate the effectiveness of the proposed algorithmic SLR methodology.
2601.03794Jan 2026
View2601.08853Kladia Liquidity Deflator (KLD): A Debt-Indexed Deflationary Token on XRPL
Kladia Liquidity Deflator (KLD) is an XRPL-based, debt-indexed token whose supply dynamics respond directly to a debt index derived from macroeconomic data sources. The model links indebtedness to deterministic adjustments in issuance, burns, and escrow release caps, creating a rule-based deflationary mechanism that strengthens as debt rises. With a fixed maximum supply of 10 billion KLD, the mechanism is implemented through XRPL oracles and governance. Escrow locking depends on the TokenEscrow amendment; until it is active network-wide, allocations will be secured in a multi-signature vault with published rules and public monitoring. KLD provides a transparent and mathematically grounded framework for a macro-responsive digital asset.
2601.08853Jan 2026
ViewPage 1 of 4
