ML Anthology

FinQA: A Training-Free Dynamic Knowledge Graph Question Answering System in Finance with LLM-Based Revision

Wenbiao Tao, Hanlun Zhu, Keren Tan, Jiani Wang, Yuanyuan Liang, Huihui Jiang, Pengcheng Yuan, Yunshi Lan
ECML-PKDD 2024 pp. 418-423
doi:10.1007/978-3-031-70371-3_32 /ecmlpkdd/2024/tao2024ecmlpkdd-finqa/

Abstract

Knowledge graph question answering (KGQA) in the finance domain aims to answer questions based on a dynamic knowledge graph (KG), which suffers from frequent updates. Moreover, the lack of high-quality annotated data renders data-driven and training-dependent approaches ineffective. To bridge the gap, we develop FinQA, which is a training-free dynamic knowledge graph question answering system in finance with large language model based (LLM-based) revision. Specifically, FinQA gives considerations to the following aspects: (1) constructing a dynamic finance knowledge graph partitioned based on data update frequencies; (2) proposing a training-free question-answering (QA) system to parse natural language to graph query language (NL2GQL) and achieving high-efficient coordination with the dynamic KG; (3) integrating the QA system with an open-source LLM to further boost the accuracy.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Tao et al. "FinQA: A Training-Free Dynamic Knowledge Graph Question Answering System in Finance with LLM-Based Revision." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2024. doi:10.1007/978-3-031-70371-3_32

Markdown

[Tao et al. "FinQA: A Training-Free Dynamic Knowledge Graph Question Answering System in Finance with LLM-Based Revision." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2024.](https://mlanthology.org/ecmlpkdd/2024/tao2024ecmlpkdd-finqa/) doi:10.1007/978-3-031-70371-3_32

BibTeX

@inproceedings{tao2024ecmlpkdd-finqa,
  title     = {{FinQA: A Training-Free Dynamic Knowledge Graph Question Answering System in Finance with LLM-Based Revision}},
  author    = {Tao, Wenbiao and Zhu, Hanlun and Tan, Keren and Wang, Jiani and Liang, Yuanyuan and Jiang, Huihui and Yuan, Pengcheng and Lan, Yunshi},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2024},
  pages     = {418-423},
  doi       = {10.1007/978-3-031-70371-3_32},
  url       = {https://mlanthology.org/ecmlpkdd/2024/tao2024ecmlpkdd-finqa/}
}