---
title: Transformer-based CoVaR: Systemic Risk in Textual Information
url: https://www.ml-quant.com/papers/repec/bri-uobdis-26-840/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-02
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:bri:uobdis:26/840
source_url: https://econpapers.repec.org/RePEc:bri:uobdis:26/840
featured: 2026-10-02
citations: unknown
topic: LLMs & Text
---


# Transformer-based CoVaR: Systemic Risk in Textual Information

Integrating financial news embeddings from large language models with market data, the study improves systemic risk forecasts using conditional value-at-risk without requiring large datasets.

- Source: https://econpapers.repec.org/RePEc:bri:uobdis:26/840
- Identifier: RePEc:bri:uobdis:26/840
- Released: 2026-09-23
- First featured: Quant Letter No. 133 (2026-10-02): https://www.ml-quant.com/issues/2026-10-02/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: LLMs & Text
- Authors: Junyu Chen, Tom Boot, Lingwei Kong, Weining Wang

## Related

- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://www.ml-quant.com/papers/arxiv/2401.15024/): Compressing Language Models: The paper introduces SliceGPT, a post-training sparsification scheme for large language models that reduces the network's embedding dimension, maintains high performance, reduces inference computation, and reveals computational invariance in transformer networks.
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://www.ml-quant.com/papers/arxiv/2405.05254/): YOCO architecture improves large language models by reducing GPU memory usage and speeding up the prefill stage, outperforming the Transformer model.
- [Efficient Adversarial Training in LLMs with Continuous Attacks](https://www.ml-quant.com/papers/arxiv/2405.15589/): CAdvUL, a new adversarial training algorithm, enhances the resilience of large language models against adversarial attacks by efficiently calculating attacks in the continuous embedding space.
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://www.ml-quant.com/papers/arxiv/2403.20327/): Compact Text Embeddings: Gecko is a new text embedding model that improves knowledge extraction from large language models, surpassing other models in the Massive Text Embedding Benchmark.
- [Interpreting the Interpreter: Can We Model post-ECB Conferences Volatility with LLM Agents?](https://www.ml-quant.com/papers/arxiv/2508.13635/): A new method using a Large Language Model can predict financial market responses to European Central Bank press conferences, aiding in maintaining financial stability.
- [The amplifier effect of artificial agents in social contagion](https://www.ml-quant.com/papers/arxiv/2502.21037/): The study shows that artificial agents, powered by large language models, can speed up social contagion due to their lower adoption thresholds, potentially accelerating societal behavioral changes.