# Converge to the Truth: Factual Error Correction via Iterative Constrained Editing

arXiv: https://arxiv.org/abs/2211.12130 · HTML: https://mlsanity.com/paper/2211.12130/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 57 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [GECToR -- Grammatical Error Correction: Tag, Not Rewrite](https://mlsanity.com/paper/2005.12592/) (2020)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://mlsanity.com/paper/1909.03242/) (2019)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Faithful to the Original: Fact Aware Neural Abstractive Summarization](https://mlsanity.com/paper/1711.04434/) (2017)
- [Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering](https://mlsanity.com/paper/2104.08202/) (2021)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [Evidence-based Factual Error Correction](https://mlsanity.com/paper/2012.15788/) (2020)
- [Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings](https://mlsanity.com/paper/2106.02736/) (2021)
- [A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction](https://mlsanity.com/paper/1801.08831/) (2018)
- [EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start](https://mlsanity.com/paper/2205.12209/) (2022)
- [Evaluating Factuality in Text Simplification](https://mlsanity.com/paper/2204.07562/) (2022)
- [LM-Critic: Language Models for Unsupervised Grammatical Error Correction](https://mlsanity.com/paper/2109.06822/) (2021)
- [Automatic Fact-guided Sentence Modification](https://mlsanity.com/paper/1909.13838/) (2019)

## Built on by (most cited first, 9 of 9)

- [Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA](https://mlsanity.com/paper/2305.14458/) (2023)
- [Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework](https://mlsanity.com/paper/2306.05119/) (2023)
- [Zero-Shot Fact Verification via Natural Logic and Large Language Models](https://mlsanity.com/paper/2410.03341/) (2024)
- [Improving Factual Error Correction by Learning to Inject Factual Errors](https://mlsanity.com/paper/2312.07049/) (2023)
- [SciFix: Outperforming GPT3 on Scientific Factual Error Correction](https://mlsanity.com/paper/2305.14707/) (2023)
- [HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models](https://mlsanity.com/paper/2509.06596/) (2025)
- [CECOR: Correction-oriented synthetic data construction for factual error correction](https://mlsanity.com/paper/2605.02277/) (2026)
- [Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://mlsanity.com/paper/2605.18776/) (2026)
- [An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection](https://mlsanity.com/paper/2606.27959/) (2026)

## Abstract (arXiv)

Given a possibly false claim sentence, how can we automatically correct it with minimal editing? Existing methods either require a large number of pairs of false and corrected claims for supervised training or do not handle well errors spanning over multiple tokens within an utterance. In this paper, we propose VENCE, a novel method for factual error correction (FEC) with minimal edits. VENCE formulates the FEC problem as iterative sampling editing actions with respect to a target density function. We carefully design the target function with predicted truthfulness scores from an offline trained fact verification model. VENCE samples the most probable editing positions based on back-calculated gradients of the truthfulness score concerning input tokens and the editing actions using a distantly-supervised language model (T5). Experiments on a public dataset show that VENCE improves the well-adopted SARI metric by 5.3 (or a relative improvement of 11.8%) over the previous best distantly-supervised methods.