Improving Event-Level Financial Sentiment Analysis with Adaptive Reasoning Order Chain-of-Thought Prompting
Intelligent Computing · 01.01.2026 · 5
DOI: 10.34133/icomputing.0651 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent Computing, online erschienen am 07.07.2026. Verfasst von Zhipeng Qian und 4 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Key R&D Plan, National Natural Science Foundation of China, Zhengzhou Collaborative Innovation Major Project.
Abstract (Originalsprache)
Event-level financial sentiment analysis (EFSA), an emerging research field of considerable interest, aims to extract quintuples of sentiment elements from given financial news articles. Preliminary studies indicate that the sequential reasoning order in chain-of-thought (CoT) prompting considerably impacts the performance of financial information extraction. We propose an adaptive reasoning order CoT framework (ARO-CoT) that enables large language models to determine the optimal query order for the extraction of financial quintuples (company, industry, coarse-grained event, fine-grained event, and sentiment) from Chinese news articles. Specifically, ARO-CoT trains models to automatically select query sequences through reasoning order adaptation, thereby yielding more precise quintuples. To validate the effectiveness of our framework, we conducted comprehensive experiments on the EFSA benchmark. Compared with the previous best EFSA results obtained by retrieval-augmented multipath chain-of-thought prompting, ARO-CoT achieves a new state-of-the-art F1 score and demonstrates robust performance across all EFSA subtasks.
Förderung
- National Key R&D Plan
- National Natural Science Foundation of China
- Zhengzhou Collaborative Innovation Major Project
Zitieren
APA
Qian, Z., Lian, J., Guo, W., Chen, T., & He, Q. (2026). Improving Event-Level Financial Sentiment Analysis with Adaptive Reasoning Order Chain-of-Thought Prompting. Intelligent Computing, 5. https://doi.org/10.34133/icomputing.0651
Vancouver
Qian Z, Lian J, Guo W, Chen T, He Q. Improving Event-Level Financial Sentiment Analysis with Adaptive Reasoning Order Chain-of-Thought Prompting. Intelligent Computing. 2026;5. doi:10.34133/icomputing.0651
BibTeX
@article{Qian2026,
author = {Qian, Zhipeng and Lian, Junhong and Guo, Weidong and Chen, Tianyu and He, Qing},
title = {Improving Event-Level Financial Sentiment Analysis with Adaptive Reasoning Order Chain-of-Thought Prompting},
journal = {Intelligent Computing},
year = {2026},
volume = {5},
doi = {10.34133/icomputing.0651}
}
EUVIMED