# LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network

arXiv: https://arxiv.org/abs/2004.13659 · HTML: https://mlsanity.com/paper/2004.13659/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 26 of 26)

- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables](https://mlsanity.com/paper/2305.13186/) (2023)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024)
- [ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples](https://mlsanity.com/paper/2210.12374/) (2022)
- [From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning](https://mlsanity.com/paper/2304.07995/) (2023)
- [Table-based Fact Verification with Self-adaptive Mixture of Experts](https://mlsanity.com/paper/2204.08753/) (2022)
- [Exploring Decomposition for Table-based Fact Verification](https://mlsanity.com/paper/2109.11020/) (2021)
- [LogiGAN: Learning Logical Reasoning via Adversarial Pre-training](https://mlsanity.com/paper/2205.08794/) (2022)
- [TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning](https://mlsanity.com/paper/2409.11724/) (2024)
- [Table-based Fact Verification with Salience-aware Learning](https://mlsanity.com/paper/2109.04053/) (2021)
- [DoT: An efficient Double Transformer for NLP tasks with tables](https://mlsanity.com/paper/2106.00479/) (2021)
- [Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification](https://mlsanity.com/paper/2109.06480/) (2021)
- [Volta at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables using TAPAS and Transfer Learning](https://mlsanity.com/paper/2106.00248/) (2021)
- [Leveraging Data Recasting to Enhance Tabular Reasoning](https://mlsanity.com/paper/2211.12641/) (2022)
- [TabVer: Tabular Fact Verification with Natural Logic](https://mlsanity.com/paper/2411.01093/) (2024)
- [TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering](https://mlsanity.com/paper/2509.01312/) (2025)
- [Are Large Language Models Table-based Fact-Checkers?](https://mlsanity.com/paper/2402.02549/) (2024)
- [BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with Tables](https://mlsanity.com/paper/2104.03071/) (2021)
- [Analyzing LLM Instruction Optimization for Tabular Fact Verification](https://mlsanity.com/paper/2602.17937/) (2026)
- [SoK: Formal Methods for Fact-Checking and Information Integrity](https://mlsanity.com/paper/2609.23239/) (2026)

## Abstract (arXiv)

Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this work, we propose LogicalFactChecker, a neural network approach capable of leveraging logical operations for fact checking. It achieves the state-of-the-art performance on TABFACT, a large-scale, benchmark dataset built for verifying a textual statement with semi-structured tables. This is achieved by a graph module network built upon the Transformer-based architecture. With a textual statement and a table as the input, LogicalFactChecker automatically derives a program (a.k.a. logical form) of the statement in a semantic parsing manner. A heterogeneous graph is then constructed to capture not only the structures of the table and the program, but also the connections between inputs with different modalities. Such a graph reveals the related contexts of each word in the statement, the table and the program. The graph is used to obtain graph-enhanced contextual representations of words in Transformer-based architecture. After that, a program-driven module network is further introduced to exploit the hierarchical structure of the program, where semantic compositionality is dynamically modeled along the program structure with a set of function-specific modules. Ablation experiments suggest that both the heterogeneous graph and the module network are important to obtain strong results.