Enhancing Fact Verification with Causal Knowledge Graphs and Transformer-Based Retrieval for Deductive Reasoning

Fiona Anting Tan, Jay Desai, Srinivasan H. Sengamedu


Abstract
The ability to extract and verify factual information from free-form text is critical in an era where vast amounts of unstructured data are available, yet unreliable sources abound. This paper focuses on enhancing causal deductive reasoning, a key component of factual verification, through the lens of accident investigation, where determining the probable causes of events is paramount. Deductive reasoning refers to the task of drawing conclusions based on a premise. While some deductive reasoning benchmarks exist, none focus on causal deductive reasoning and are from real-world applications. Recently, large language models (LLMs) used with prompt engineering techniques like retrieval-augmented generation (RAG) have demonstrated remarkable performance across various natural language processing benchmarks. However, adapting these techniques to handle scenarios with no knowledge bases and to different data structures, such as graphs, remains an ongoing challenge. In our study, we introduce a novel framework leveraging LLMs’ decent ability to detect and infer causal relations to construct a causal Knowledge Graph (KG) which represents knowledge that the LLM recognizes. Additionally, we propose a RoBERTa-based Transformer Graph Neural Network (RoTG) specifically designed to select relevant nodes within this KG. Integrating RoTG-retrieved causal chains into prompts effectively enhances LLM performance, demonstrating usefulness of our approach in advancing LLMs’ causal deductive reasoning capabilities.
Anthology ID:
2024.fever-1.20
Volume:
Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Michael Schlichtkrull, Yulong Chen, Chenxi Whitehouse, Zhenyun Deng, Mubashara Akhtar, Rami Aly, Zhijiang Guo, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal, James Thorne, Andreas Vlachos
Venue:
FEVER
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
151–169
Language:
URL:
https://aclanthology.org/2024.fever-1.20
DOI:
Bibkey:
Cite (ACL):
Fiona Anting Tan, Jay Desai, and Srinivasan H. Sengamedu. 2024. Enhancing Fact Verification with Causal Knowledge Graphs and Transformer-Based Retrieval for Deductive Reasoning. In Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER), pages 151–169, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Enhancing Fact Verification with Causal Knowledge Graphs and Transformer-Based Retrieval for Deductive Reasoning (Tan et al., FEVER 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.fever-1.20.pdf