Junyu Chen, Tom Boot, Lingwei Kong, Weining Wang
arXiv 13 Feb 2026 · Econometrics
arXiv:2602.12490 · PDF · DOI · OpenAlex · Extracted main text
Conditional Value-at-Risk (CoVaR) quantifies systemic financial risk by measuring the loss quantile of one asset, conditional on another asset experiencing distress. We develop a Transformer-based methodology that integrates financial news articles directly with market data to improve CoVaR estimates. Unlike approaches that use predefined sentiment scores, our method incorporates raw text embeddings generated by a large language model (LLM). We prove explicit error bounds for our Transformer CoVaR estimator, showing that accurate CoVaR learning is possible even with small datasets. Using U.S. market returns and Reuters news items from 2006--2013, our out-of-sample results show that textual information impacts the CoVaR forecasts. With better predictive performance, we identify a pronounced negative dip during market stress periods across several equity assets when comparing the Transformer-based CoVaR to both the CoVaR without text and the CoVaR using traditional sentiment measures. Our results show that textual data can be used to effectively model systemic risk without requiring prohibitively large data sets.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Edelman, Benjamin and Goel, Surbhi and Kakade, Sham and Zhang, Cyril (2022) Inductive Biases and Variable Creation in Self-Attention Mechanisms | 1.000 | 20 | 5 | 100% |
| 2 | Adrian, Tobias and Brunnermeier, Markus K (2016) CoVaR | 1.000 | 8 | 3 | 100% |
| 3 | Schmidt-Hieber, Johannes (2020) Nonparametric regression using deep neural networks with ReLU activation function | 1.000 | 6 | 4 | 100% |
| 4 | Wolfgang Karl Härdle and Weining Wang and Lining Yu (2016) TENET: Tail-Event driven NETwork risk self | 0.928 | 4 | 3 | 100% |
| 5 | Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Ja… (2017) Attention is All You Need | 0.928 | 4 | 3 | 100% |
| 6 | Oscar Hernan Madrid Padilla and Wesley Tansey and Yanzhen Chen (2022) Quantile regression with ReLU Networks: Estimators and minimax rates | 0.928 | 4 | 3 | 100% |
| 7 | Tetlock, Paul (2007) Giving Content to Investor Sentiment: The Role of Media in the Stock Market | 0.843 | 3 | 3 | 100% |
| 8 | Loughran, Tim and McDonald, Bill (2011) When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks | 0.843 | 3 | 3 | 100% |
| 9 | Keilbar, Georg and Wang, Weining (2022) Modelling Systemic Risk Using Neural Network Quantile Regression self | 0.843 | 3 | 3 | 100% |
| 10 | Trauger, Jacob and Tewari, Ambuj (2024) Sequence Length Independent Norm-Based Generalization Bounds for Transformers | 0.811 | 4 | 2 | 100% |
Showing the top 10 of 83 scored citations.