# Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News

arXiv: https://arxiv.org/abs/2104.12918 · HTML: https://mlsanity.com/paper/2104.12918/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Generating Fact Checking Explanations](https://mlsanity.com/paper/2004.05773/) (2020)
- [Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1907.05774/) (2019)
- [GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media](https://mlsanity.com/paper/2004.11648/) (2020)
- [Automated Fact Checking: Task formulations, methods and future directions](https://mlsanity.com/paper/1806.07687/) (2018)
- [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://mlsanity.com/paper/2005.12116/) (2020)
- [Consistency of a Recurrent Language Model With Respect to Incomplete Decoding](https://mlsanity.com/paper/2002.02492/) (2020)
- [Generating Fact Checking Briefs](https://mlsanity.com/paper/2011.05448/) (2020)
- [Biased TextRank: Unsupervised Graph-Based Content Extraction](https://mlsanity.com/paper/2011.01026/) (2020)

## Built on by (most cited first, 8 of 8)

- [End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models](https://mlsanity.com/paper/2205.12487/) (2022)
- [Matching Tweets With Applicable Fact-Checks Across Languages](https://mlsanity.com/paper/2202.07094/) (2022)
- [Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI](https://mlsanity.com/paper/2308.07213/) (2023)
- [Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models](https://mlsanity.com/paper/2305.12544/) (2023)
- [Like Article, Like Audience: Enforcing Multimodal Correlations for Disinformation Detection](https://mlsanity.com/paper/2108.13892/) (2021)
- [Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions](https://mlsanity.com/paper/2410.20019/) (2024)
- [Assessing Effectiveness of Using Internal Signals for Check-Worthy Claim Identification in Unlabeled Data for Automated Fact-Checking](https://mlsanity.com/paper/2111.01706/) (2021)
- [Generating Zero-shot Abstractive Explanations for Rumour Verification](https://mlsanity.com/paper/2401.12713/) (2024)

## Abstract (arXiv)

In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.