# Document-level Claim Extraction and Decontextualisation for Fact-Checking

arXiv: https://arxiv.org/abs/2406.03239 · HTML: https://mlsanity.com/paper/2406.03239/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://mlsanity.com/paper/1809.02922/) (2018)
- [DocNLI: A Large-scale Dataset for Document-level Natural Language Inference](https://mlsanity.com/paper/2106.09449/) (2021)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection](https://mlsanity.com/paper/1809.08193/) (2018)
- [MixQG: Neural Question Generation with Mixed Answer Types](https://mlsanity.com/paper/2110.08175/) (2021)
- [A Benchmark Dataset of Check-worthy Factual Claims](https://mlsanity.com/paper/2004.14425/) (2020)
- [Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter](https://mlsanity.com/paper/2210.04710/) (2022)
- [Claim Detection in Biomedical Twitter Posts](https://mlsanity.com/paper/2104.11639/) (2021)
- [From Chaos to Clarity: Claim Normalization to Empower Fact-Checking](https://mlsanity.com/paper/2310.14338/) (2023)

## Built on by (most cited first, 6 of 6)

- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [Scalable and Domain-General Abstractive Proposition Segmentation](https://mlsanity.com/paper/2406.19803/) (2024)
- [EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval](https://mlsanity.com/paper/2504.06269/) (2025)
- [Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine](https://mlsanity.com/paper/2506.20876/) (2025)
- [Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning](https://mlsanity.com/paper/2509.17921/) (2025)
- [Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak](https://mlsanity.com/paper/2511.14566/) (2025)

## Abstract (arXiv)

Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims. However, existing claim extraction approaches focus more on identifying and extracting claims from individual sentences, e.g., identifying whether a sentence contains a claim or the exact boundaries of the claim within a sentence. In this paper, we propose a method for document-level claim extraction for fact-checking, which aims to extract check-worthy claims from documents and decontextualise them so that they can be understood out of context. Specifically, we first recast claim extraction as extractive summarization in order to identify central sentences from documents, then rewrite them to include necessary context from the originating document through sentence decontextualisation. Evaluation with both automatic metrics and a fact-checking professional shows that our method is able to extract check-worthy claims from documents more accurately than previous work, while also improving evidence retrieval.