# Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment

arXiv: https://arxiv.org/abs/2403.02698 · HTML: https://mlsanity.com/paper/2403.02698/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 36 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 4 of 4)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Causal Intervention Improves Implicit Sentiment Analysis](https://mlsanity.com/paper/2208.09329/) (2022)

## Built on by (most cited first, 17 of 17)

- [On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification](https://mlsanity.com/paper/2508.05629/) (2025)
- [Web Retrieval Agents for Evidence-Based Misinformation Detection](https://mlsanity.com/paper/2409.00009/) (2024)
- [CHECKWHY: Causal Fact Verification via Argument Structure](https://mlsanity.com/paper/2408.10918/) (2024)
- [Resilient Contrastive Pre-training under Non-Stationary Drift](https://mlsanity.com/paper/2502.07620/) (2025)
- [LIVE: Learnable In-Context Vector for Visual Question Answering](https://mlsanity.com/paper/2406.13185/) (2024)
- [CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking](https://mlsanity.com/paper/2502.09635/) (2025)
- [Adversarial Attacks Against Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2509.08463/) (2025)
- [Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning](https://mlsanity.com/paper/2505.13081/) (2025)
- [Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification](https://mlsanity.com/paper/2506.07446/) (2025)
- [LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection](https://mlsanity.com/paper/2604.04815/) (2026)
- [Reasoning Paths as Signals: Augmenting Multi-hop Fact Verification through Structural Reasoning Progression](https://mlsanity.com/paper/2506.07075/) (2025)
- [Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction](https://mlsanity.com/paper/2405.12579/) (2024)
- [MuPlon: Multi-Path Causal Optimization for Claim Verification through Controlling Confounding](https://mlsanity.com/paper/2509.25715/) (2025)
- [MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrieval](https://mlsanity.com/paper/2602.10023/) (2026)
- [UGID: Unified Graph Isomorphism for Debiasing Large Language Models](https://mlsanity.com/paper/2603.19144/) (2026)
- [When Verification Fails: How Compositionally Infeasible Claims Escape Rejection](https://mlsanity.com/paper/2604.10990/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

Conventional multi-hop fact verification models are prone to rely on spurious correlations from the annotation artifacts, leading to an obvious performance decline on unbiased datasets. Among the various debiasing works, the causal inference-based methods become popular by performing theoretically guaranteed debiasing such as casual intervention or counterfactual reasoning. However, existing causal inference-based debiasing methods, which mainly formulate fact verification as a single-hop reasoning task to tackle shallow bias patterns, cannot deal with the complicated bias patterns hidden in multiple hops of evidence. To address the challenge, we propose Causal Walk, a novel method for debiasing multi-hop fact verification from a causal perspective with front-door adjustment. Specifically, in the structural causal model, the reasoning path between the treatment (the input claim-evidence graph) and the outcome (the veracity label) is introduced as the mediator to block the confounder. With the front-door adjustment, the causal effect between the treatment and the outcome is decomposed into the causal effect between the treatment and the mediator, which is estimated by applying the idea of random walk, and the causal effect between the mediator and the outcome, which is estimated with normalized weighted geometric mean approximation. To investigate the effectiveness of the proposed method, an adversarial multi-hop fact verification dataset and a symmetric multi-hop fact verification dataset are proposed with the help of the large language model. Experimental results show that Causal Walk outperforms some previous debiasing methods on both existing datasets and the newly constructed datasets. Code and data will be released at https://github.com/zcccccz/CausalWalk.