Institution profile

Southwestern University of Finance and Economics

Academic institutionasia · cn
Official website
Research library161linked papers
Opportunities0open roles
Selected work

Representative Papers

FinTruthQA: A Benchmark Dataset for Evaluating the Quality of Financial Information Disclosure

Jun 17, 2024arXiv.org

The absence of automated tools for evaluating financial disclosure quality in Q&A forums on Chinese investor interaction platforms hinders regulatory oversight and market transparency. Method: We introduce FinDisclose-QA, the first benchmark for assessing financial disclosure quality in Chinese capital markets, comprising 6,000 real-world question-answer pairs manually annotated across four dimensions—completeness, accuracy, readability, and substantive relevance. We formally define and quantify multi-dimensional disclosure quality metrics specific to Q&A contexts and conduct multi-task evaluation using both traditional NLP models and large language models (LLMs) for question identification, answer relevance, readability, and substantive relevance assessment. Results: Experiments reveal that existing models perform well on question understanding but exhibit significant deficiencies in evaluating answer readability and substantive relevance. FinDisclose-QA provides a reproducible, extensible evaluation infrastructure for regtech applications, auditing practice, and academic research in financial communication.

2 citationsRead paper

HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval

Jan 22, 2026

Existing text-to-video retrieval methods struggle to distinguish salient visual content from background noise under sparse textual queries, leading to inefficient cross-modal feature interaction. Inspired by human visual cognition, this work proposes a coarse-to-fine alignment framework that introduces, for the first time, both macro- and micro-perception mechanisms into video representation learning. Specifically, a Frame-Level Filtering Module (FFSM) eliminates temporal redundancy, while a Patch-Level Focusing and Compression Module (PFCM) aggregates salient visual entities, collectively emulating human-like visual attention. The proposed approach achieves state-of-the-art performance across five benchmark datasets, significantly improving both retrieval accuracy and semantic alignment between text and video modalities.

1 citationsRead paper

Forecasting realized volatility in the stock market: a path-dependent perspective

Mar 02, 2025

To address insufficient predictive accuracy for stock market realized volatility, this paper proposes the HAR-PD model family, which integrates path-dependence characteristics into the Heterogeneous Autoregressive (HAR) framework—marking the first incorporation of path-dependent volatility decomposition into HAR modeling. The core innovation is the HAR-REQ model, which dynamically identifies trend and reversal patterns in price paths using empirically determined quantile thresholds, thereby explicitly capturing volatility’s long- and short-term memory effects and asymmetric responses. Empirical analysis on high-frequency data from the Shanghai and Shenzhen stock markets demonstrates that HAR-PD models significantly outperform the benchmark HAR model, reducing average MAE by 12.6% and RMSE by 11.3%. Robustness is confirmed through rolling-window estimation, subsample analysis, and alternative volatility measures. This work introduces a novel path-dependent perspective to volatility modeling and provides an interpretable, statistically grounded toolkit for practitioners and researchers.

1 citationsRead paper

Autoregressive Networks with Dependent Edges

Apr 24, 2024

This paper addresses the challenge of edge-dependent modeling in dynamic networks by proposing an autoregressive Exponential Random Graph Model (ERGM) framework that balances interpretability and computational efficiency. Methodologically, it introduces a conditional independence assumption to accommodate realistic network features—including transitivity, degree heterogeneity, and density dependence—designs an iterative projection estimator to mitigate slow convergence under high-dimensional parameters, and derives a martingale difference structure under non-stationarity, yielding non-normal asymptotic distributions (reducing to normality only under mixing conditions). Theoretically, it breaks classical maximum likelihood estimation’s implicit reliance on stationarity and asymptotic normality. Empirically, the estimator demonstrates rapid convergence, statistical validity, and strong robustness in simulations and real-world dynamic networks—including academic collaboration and information diffusion—significantly enhancing modeling efficiency and practical applicability for dynamic network analysis.

1 citationsRead paper
Recent publications

Latest Papers