# Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing

arXiv: https://arxiv.org/abs/2112.06924 · HTML: https://mlsanity.com/paper/2112.06924/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://mlsanity.com/paper/1909.03242/) (2019)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [Generating Fact Checking Explanations](https://mlsanity.com/paper/2004.05773/) (2020)
- [Sentence Simplification with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.10931/) (2017)
- [GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media](https://mlsanity.com/paper/2004.11648/) (2020)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [Unsupervised Paraphrasing by Simulated Annealing](https://mlsanity.com/paper/1909.03588/) (2019)
- [Unsupervised Text Generation by Learning from Search](https://mlsanity.com/paper/2007.08557/) (2020)
- [Iterative Edit-Based Unsupervised Sentence Simplification](https://mlsanity.com/paper/2006.09639/) (2020)
- [Generating Label Cohesive and Well-Formed Adversarial Claims](https://mlsanity.com/paper/2009.08205/) (2020)
- [Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction](https://mlsanity.com/paper/2005.01791/) (2020)
- [Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification](https://mlsanity.com/paper/1904.02767/) (2019)
- [DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification](https://mlsanity.com/paper/2004.13455/) (2020)

## Built on by (most cited first, 15 of 15)

- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification](https://mlsanity.com/paper/2310.09754/) (2023)
- [QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking](https://mlsanity.com/paper/2310.07609/) (2023)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches](https://mlsanity.com/paper/2407.12853/) (2024)
- [Unsupervised Pretraining for Fact Verification by Language Model Distillation](https://mlsanity.com/paper/2309.16540/) (2023)
- [Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework](https://mlsanity.com/paper/2406.15085/) (2024)
- [Robust Claim Verification Through Fact Detection](https://mlsanity.com/paper/2407.18367/) (2024)
- [Graph-Guided Textual Explanation Generation Framework](https://mlsanity.com/paper/2412.12318/) (2024)
- [Evidence-based Interpretable Open-domain Fact-checking with Large Language Models](https://mlsanity.com/paper/2312.05834/) (2023)
- [Generating Zero-shot Abstractive Explanations for Rumour Verification](https://mlsanity.com/paper/2401.12713/) (2024)
- [Explaining Sources of Uncertainty in Automated Fact-Checking](https://mlsanity.com/paper/2505.17855/) (2025)
- [From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence](https://mlsanity.com/paper/2605.06006/) (2026)
- [The Alignment Bottleneck in Decomposition-Based Claim Verification](https://mlsanity.com/paper/2602.10380/) (2026)

## Abstract (arXiv)

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is expensive and time-consuming. Recent works frame explanation generation as extractive summarization, and propose to automatically select a sufficient subset of the most important facts from the ruling comments (RCs) of a professional journalist to obtain fact-checking explanations. However, these explanations lack fluency and sentence coherence. In this work, we present an iterative edit-based algorithm that uses only phrase-level edits to perform unsupervised post-editing of disconnected RCs. To regulate our editing algorithm, we use a scoring function with components including fluency and semantic preservation. In addition, we show the applicability of our approach in a completely unsupervised setting. We experiment with two benchmark datasets, LIAR-PLUS and PubHealth. We show that our model generates explanations that are fluent, readable, non-redundant, and cover important information for the fact check.