# Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification

arXiv: https://arxiv.org/abs/2305.09400 · HTML: https://mlsanity.com/paper/2305.09400/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 50 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 30 of 41)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Generating Fact Checking Explanations](https://mlsanity.com/paper/2004.05773/) (2020)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://mlsanity.com/paper/1910.09796/) (2019)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning](https://mlsanity.com/paper/1809.06416/) (2018)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction](https://mlsanity.com/paper/2005.00652/) (2020)
- [How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking](https://mlsanity.com/paper/2004.14992/) (2020)
- [Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval](https://mlsanity.com/paper/2101.00436/) (2021)
- [Did the Model Understand the Question?](https://mlsanity.com/paper/1805.05492/) (2018)
- [Multi-Hop Fact Checking of Political Claims](https://mlsanity.com/paper/2009.06401/) (2020)
- [Understanding Interlocking Dynamics of Cooperative Rationalization](https://mlsanity.com/paper/2110.13880/) (2021)
- [Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers](https://mlsanity.com/paper/2010.00667/) (2020)
- [XFake: Explainable Fake News Detector with Visualizations](https://mlsanity.com/paper/1907.07757/) (2019)

## Built on by (most cited first, 3 of 3)

- [A Survey on Natural Language Counterfactual Generation](https://mlsanity.com/paper/2407.03993/) (2024)
- [EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification](https://mlsanity.com/paper/2310.14508/) (2023)
- [Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification](https://mlsanity.com/paper/2506.07446/) (2025)

## Abstract (arXiv)

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency and faithfulness for explainable multi-hop fact verification. In particular, given a pretrained veracity prediction model, both the token-level explainer and sentence-level explainer are trained simultaneously to obtain multi-granular rationales via differentiable masking. Meanwhile, three diagnostic properties (fidelity, consistency, salience) are introduced and applied to the training process, to ensure that the extracted rationales satisfy faithfulness and consistency. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms some state-of-the-art baselines.