Bimodal Dynamics of the Artificial Limit Order Book Stock Exchange with Autonomous Traders ArXiv ID: 2508.17837 “View on arXiv” Authors: Matej Steinbacher, Mitja Steinbacher, Matjaz Steinbacher Abstract This paper explores the bifurcative dynamics of an artificial stock market exchange (ASME) with endogenous, myopic traders interacting through a limit order book (LOB). We showed that agent-based price dynamics possess intrinsic bistability, which is not a result of randomness but an emergent property of micro-level trading rules, where even identical initial conditions lead to qualitatively different long-run price equilibria: a deterministic zero-price state and a persistent positive-price equilibrium. The study also identifies a metastable region with elevated volatility between the basins of attraction and reveals distinct transient behaviors for trajectories converging to these equilibria. Furthermore, we observe that the system is neither entirely regular nor fully chaotic. By highlighting the emergence of divergent market outcomes from uniform beginnings, this work contributes a novel perspective on the inherent path dependence and complex dynamics of artificial stock markets. ...

FinReflectKG: Agentic Construction and Evaluation of Financial Knowledge Graphs ArXiv ID: 2508.17906 “View on arXiv” Authors: Abhinav Arun, Fabrizio Dimino, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali Abstract The financial domain poses unique challenges for knowledge graph (KG) construction at scale due to the complexity and regulatory nature of financial documents. Despite the critical importance of structured financial knowledge, the field lacks large-scale, open-source datasets capturing rich semantic relationships from corporate disclosures. We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S and P 100 companies - a comprehensive resource designed to catalyze research in financial AI. We propose a robust and generalizable knowledge graph (KG) construction framework that integrates intelligent document parsing, table-aware chunking, and schema-guided iterative extraction with a reflection-driven feedback loop. Our system incorporates a comprehensive evaluation pipeline, combining rule-based checks, statistical validation, and LLM-as-a-Judge assessments to holistically measure extraction quality. We support three extraction modes - single-pass, multi-pass, and reflection-agent-based - allowing flexible trade-offs between efficiency, accuracy, and reliability based on user requirements. Empirical evaluations demonstrate that the reflection-agent-based mode consistently achieves the best balance, attaining a 64.8 percent compliance score against all rule-based policies (CheckRules) and outperforming baseline methods (single-pass and multi-pass) across key metrics such as precision, comprehensiveness, and relevance in LLM-guided evaluations. ...

Tracing Positional Bias in Financial Decision-Making: Mechanistic Insights from Qwen2.5 ArXiv ID: 2508.18427 “View on arXiv” Authors: Fabrizio Dimino, Krati Saxena, Bhaskarjit Sarmah, Stefano Pasquali Abstract The growing adoption of large language models (LLMs) in finance exposes high-stakes decision-making to subtle, underexamined positional biases. The complexity and opacity of modern model architectures compound this risk. We present the first unified framework and benchmark that not only detects and quantifies positional bias in binary financial decisions but also pinpoints its mechanistic origins within open-source Qwen2.5-instruct models (1.5B-14B). Our empirical analysis covers a novel, finance-authentic dataset revealing that positional bias is pervasive, scale-sensitive, and prone to resurfacing under nuanced prompt designs and investment scenarios, with recency and primacy effects revealing new vulnerabilities in risk-laden contexts. Through transparent mechanistic interpretability, we map how and where bias emerges and propagates within the models to deliver actionable, generalizable insights across prompt types and scales. By bridging domain-specific audit with model interpretability, our work provides a new methodological standard for both rigorous bias diagnosis and practical mitigation, establishing essential guidance for responsible and trustworthy deployment of LLMs in financial systems. ...

Detecting Multilevel Manipulation from Limit Order Book via Cascaded Contrastive Representation Learning ArXiv ID: 2508.17086 “View on arXiv” Authors: Yushi Lin, Peng Yang Abstract Trade-based manipulation (TBM) undermines the fairness and stability of financial markets drastically. Spoofing, one of the most covert and deceptive TBM strategies, exhibits complex anomaly patterns across multilevel prices, while often being simplified as a single-level manipulation. These patterns are usually concealed within the rich, hierarchical information of the Limit Order Book (LOB), which is challenging to leverage due to high dimensionality and noise. To address this, we propose a representation learning framework combining a cascaded LOB representation architecture with supervised contrastive learning. Extensive experiments demonstrate that our framework consistently improves detection performance across diverse models, with Transformer-based architectures achieving state-of-the-art results. In addition, we conduct systematic analyses and ablation studies to investigate multilevel manipulation and the contributions of key components for detection, offering broader insights into representation learning and anomaly detection for complex time series data. ...

Risk-Neutral Pricing of Random-Expiry Options Using Trinomial Trees ArXiv ID: 2508.17014 “View on arXiv” Authors: Sebastien Bossu, Michael Grabchak Abstract Random-expiry options are nontraditional derivative contracts that may expire early based on a random event. We develop a methodology for pricing these options using a trinomial tree, where the middle path is interpreted as early expiry. We establish that this approach is free of arbitrage, derive its continuous-time limit, and show how it may be implemented numerically in an efficient manner. ...

THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics ArXiv ID: 2508.16936 “View on arXiv” Authors: Hoyoung Lee, Wonbin Ahn, Suhwan Park, Jaehoon Lee, Minjae Kim, Sungdong Yoo, Taeyoon Lim, Woohyung Lim, Yongjae Lee Abstract Thematic investing, which aims to construct portfolios aligned with structural trends, remains a challenging endeavor due to overlapping sector boundaries and evolving market dynamics. A promising direction is to build semantic representations of investment themes from textual data. However, despite their power, general-purpose LLM embedding models are not well-suited to capture the nuanced characteristics of financial assets, since the semantic representation of investment assets may differ fundamentally from that of general financial text. To address this, we introduce THEME, a framework that fine-tunes embeddings using hierarchical contrastive learning. THEME aligns themes and their constituent stocks using their hierarchical relationship, and subsequently refines these embeddings by incorporating stock returns. This process yields representations effective for retrieving thematically aligned assets with strong return potential. Empirical results demonstrate that THEME excels in two key areas. For thematic asset retrieval, it significantly outperforms leading large language models. Furthermore, its constructed portfolios demonstrate compelling performance. By jointly modeling thematic relationships from text and market dynamics from returns, THEME generates stock embeddings specifically tailored for a wide range of practical investment applications. ...

Asymmetric super-Heston-rough volatility model with Zumbach effect as scaling limit of quadratic Hawkes processes ArXiv ID: 2508.16566 “View on arXiv” Authors: Priyanka Chudasama, Srikanth Krishnan Iyer Abstract Hawkes processes were first introduced to obtain microscopic models for the rough volatility observed in asset prices. Scaling limits of such processes leads to the rough-Heston model that describes the macroscopic behavior. Blanc et al. (2017) show that Time-reversal asymmetry (TRA) or the Zumbach effect can be modeled using Quadratic Hawkes (QHawkes) processes. Dandapani et al. (2021) obtain a super-rough-Heston model as scaling limit of QHawkes processes in the case where the impact of buying and selling actions are symmetric. To model asymmetry in buying and selling actions, we propose a bivariate QHawkes process and derive a super-rough-Heston model as scaling limits for the price process in the stable and near-unstable regimes that preserves TRA. A new feature of the limiting process in the near-unstable regime is that the two driving Brownian motions exhibit a stochastic covariation that depends on the spot volatility. ...

On a multivariate extension for Copula-based Conditional Value at Risk ArXiv ID: 2508.16132 “View on arXiv” Authors: Andres Mauricio Molina Barreto Abstract Copula-based Conditional Value at Risk (CCVaR) is defined as an alternative version of the classical Conditional Value at Risk (CVaR) for multivariate random vectors intended to be real-valued. We aim to generalize CCVaR to several dimensions (d>=2) when the dependence structure is given by an Archimedean copula. While previous research focused on the bivariate case, leaving the multivariate version unexplored, an almost closed-form expression for CCVaR under an Archimedean copula is derived. The conditions under which this risk measure satisfies coherence are then examined. Finally, numerical experiments based on real data are conducted to estimate CCVaR, and the results are compared with classical measures of Value at Risk (VaR) and Conditional Value at Risk (CVaR). ...

Sentiment-Aware Mean-Variance Portfolio Optimization for Cryptocurrencies ArXiv ID: 2508.16378 “View on arXiv” Authors: Qizhao Chen Abstract This paper presents a dynamic cryptocurrency portfolio optimization strategy that integrates technical indicators and sentiment analysis to enhance investment decision-making. The proposed method employs the 14-day Relative Strength Index (RSI) and 14-day Simple Moving Average (SMA) to capture market momentum, while sentiment scores are extracted from news articles using the VADER (Valence Aware Dictionary and sEntiment Reasoner) model, with compound scores quantifying overall market tone. The large language model Google Gemini is used to further verify the sentiment scores predicted by VADER and give investment decisions. These technical indicator and sentiment signals are incorporated into the expected return estimates before applying mean-variance optimization with constraints on asset weights. The strategy is evaluated through a rolling-window backtest over cryptocurrency market data, with Bitcoin (BTC) and an equal-weighted portfolio of selected cryptocurrencies serving as benchmarks. Experimental results show that the proposed approach achieves a cumulative return of 38.72, substantially exceeding Bitcoin’s 8.85 and the equal-weighted portfolio’s 21.65 over the same period, and delivers a higher Sharpe ratio (1.1093 vs. 0.8853 and 1.0194, respectively). However, the strategy exhibits a larger maximum drawdown (-18.52%) compared to Bitcoin (-4.48%) and the equal-weighted portfolio (-11.02%), indicating higher short-term downside risk. These results highlight the potential of combining sentiment and technical signals to improve cryptocurrency portfolio performance, while also emphasizing the need to address risk exposure in volatile markets. ...

Non-parametric Causal Discovery for EU Allowances Returns Through the Information Imbalance ArXiv ID: 2508.15667 “View on arXiv” Authors: Cristiano Salvagnin, Vittorio del Tatto, Maria Elena De Giuli, Antonietta Mira, Aldo Glielmo Abstract We propose to use a recently introduced non-parametric tool named Differentiable Information Imbalance (DII) to identify variables that are causally related – potentially through non-linear relationships – to the financial returns of the European Union Allowances (EUAs) within the EU Emissions Trading System (EU ETS). We examine data from January 2013 to April 2024 and compare the DII approach with multivariate Granger causality, a well-known linear approach based on VAR models. We find significant overlap among the causal variables identified by linear and non-linear methods, such as the coal futures prices and the IBEX35 index. We also find important differences between the two causal sets identified. On two synthetic datasets, we show how these differences could originate from limitations of the linear methodology. ...