# Automatic Fact-guided Sentence Modification

arXiv: https://arxiv.org/abs/1909.13838 · HTML: https://mlsanity.com/paper/1909.13838/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 28 of 28)

- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters](https://mlsanity.com/paper/2204.07447/) (2022)
- [Zero-shot Faithful Factual Error Correction](https://mlsanity.com/paper/2305.07982/) (2023)
- [NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge](https://mlsanity.com/paper/2206.07106/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction](https://mlsanity.com/paper/2207.14116/) (2022)
- [Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems](https://mlsanity.com/paper/2209.03755/) (2022)
- [Converge to the Truth: Factual Error Correction via Iterative Constrained Editing](https://mlsanity.com/paper/2211.12130/) (2022)
- [Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework](https://mlsanity.com/paper/2306.05119/) (2023)
- [Nutri-bullets: Summarizing Health Studies by Composing Segments](https://mlsanity.com/paper/2103.11921/) (2021)
- [WINELL: Wikipedia Never-Ending Updating with LLM Agents](https://mlsanity.com/paper/2508.03728/) (2025)
- [FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness](https://mlsanity.com/paper/2211.00294/) (2022)
- [Improving Factual Error Correction by Learning to Inject Factual Errors](https://mlsanity.com/paper/2312.07049/) (2023)
- [Nutribullets Hybrid: Multi-document Health Summarization](https://mlsanity.com/paper/2104.03465/) (2021)
- [Generating Related Work](https://mlsanity.com/paper/2104.08668/) (2021)
- [InfoSync: Information Synchronization across Multilingual Semi-structured Tables](https://mlsanity.com/paper/2307.03313/) (2023)
- [Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion](https://mlsanity.com/paper/2410.10408/) (2024)
- [NewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)](https://mlsanity.com/paper/2104.09647/) (2021)
- [SciFix: Outperforming GPT3 on Scientific Factual Error Correction](https://mlsanity.com/paper/2305.14707/) (2023)
- [Evidence-based Factual Error Correction](https://mlsanity.com/paper/2106.01072/) (2021)
- [Toward Machine Interpreting: Lessons from Human Interpreting Studies](https://mlsanity.com/paper/2508.07964/) (2025)
- [Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://mlsanity.com/paper/2605.18776/) (2026)

## Abstract (arXiv)

Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically changing articles. This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document. To this end, we propose a two-step solution: (1) We identify and remove the contradicting components in a target text for a given claim, using a neutralizing stance model; (2) We expand the remaining text to be consistent with the given claim, using a novel two-encoder sequence-to-sequence model with copy attention. Applied to a Wikipedia fact update dataset, our method successfully generates updated sentences for new claims, achieving the highest SARI score. Furthermore, we demonstrate that generating synthetic data through such rewritten sentences can successfully augment the FEVER fact-checking training dataset, leading to a relative error reduction of 13%.