# Learning to Revise References for Faithful Summarization

arXiv: https://arxiv.org/abs/2204.10290 · HTML: https://mlsanity.com/paper/2204.10290/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 88 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 30 of 60)

- [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)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [Lessons from Natural Language Inference in the Clinical Domain](https://mlsanity.com/paper/1808.06752/) (2018)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Evaluating Factuality in Generation with Dependency-level Entailment](https://mlsanity.com/paper/2010.05478/) (2020)
- [CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2109.09209/) (2021)
- [Entity-level Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/2102.09130/) (2021)
- [Ethical Machine Learning in Health Care](https://mlsanity.com/paper/2009.10576/) (2020)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Factual Error Correction for Abstractive Summarization Models](https://mlsanity.com/paper/2010.08712/) (2020)
- [SciFive: a text-to-text transformer model for biomedical literature](https://mlsanity.com/paper/2106.03598/) (2021)
- [Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://mlsanity.com/paper/1911.02541/) (2019)
- [Answers Unite! Unsupervised Metrics for Reinforced Summarization Models](https://mlsanity.com/paper/1909.01610/) (2019)
- [Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary](https://mlsanity.com/paper/2010.00490/) (2020)
- [Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data](https://mlsanity.com/paper/2010.05873/) (2020)

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

- [From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting](https://mlsanity.com/paper/2309.04269/) (2023)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling](https://mlsanity.com/paper/2210.12378/) (2022)
- [On Improving Summarization Factual Consistency from Natural Language Feedback](https://mlsanity.com/paper/2212.09968/) (2022)
- [Zero-shot Faithful Factual Error Correction](https://mlsanity.com/paper/2305.07982/) (2023)
- [PaniniQA: Enhancing Patient Education Through Interactive Question Answering](https://mlsanity.com/paper/2308.03253/) (2023)
- [Overview of the First Shared Task on Clinical Text Generation: RRG24 and "Discharge Me!"](https://mlsanity.com/paper/2409.16603/) (2024)
- [A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization](https://mlsanity.com/paper/2303.03948/) (2023)
- [Improving Factual Consistency in Summarization with Compression-Based Post-Editing](https://mlsanity.com/paper/2211.06196/) (2022)
- [SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization](https://mlsanity.com/paper/2402.13919/) (2024)
- [SWING: Balancing Coverage and Faithfulness for Dialogue Summarization](https://mlsanity.com/paper/2301.10483/) (2023)
- [Generating EDU Extracts for Plan-Guided Summary Re-Ranking](https://mlsanity.com/paper/2305.17779/) (2023)
- [FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization](https://mlsanity.com/paper/2311.02271/) (2023)
- [What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization](https://mlsanity.com/paper/2305.07615/) (2023)
- [Key-Element-Informed sLLM Tuning for Document Summarization](https://mlsanity.com/paper/2406.04625/) (2024)
- [Improving Summarization with Human Edits](https://mlsanity.com/paper/2310.05857/) (2023)
- [A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models](https://mlsanity.com/paper/2402.15422/) (2024)
- [Factual Dialogue Summarization via Learning from Large Language Models](https://mlsanity.com/paper/2406.14709/) (2024)
- [SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval](https://mlsanity.com/paper/2401.02369/) (2024)
- [Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation](https://mlsanity.com/paper/2510.07629/) (2025)
- [Neural Summarization of Electronic Health Records](https://mlsanity.com/paper/2305.15222/) (2023)
- [Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding](https://mlsanity.com/paper/2310.11191/) (2023)
- [On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization](https://mlsanity.com/paper/2403.05788/) (2024)
- [Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries](https://mlsanity.com/paper/2311.09458/) (2023)
- [Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization](https://mlsanity.com/paper/2312.06022/) (2023)
- [Query-Guided Self-Supervised Summarization of Nursing Notes](https://mlsanity.com/paper/2407.04125/) (2024)
- [Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://mlsanity.com/paper/2605.18776/) (2026)
- [Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models](https://mlsanity.com/paper/2608.09109/) (2026)

## Abstract (arXiv)

In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce model hallucinations. Yet, for smaller, and/or noisier corpora, filtering is detrimental to performance. To improve reference quality while retaining all data, we propose a new approach: to selectively re-write unsupported reference sentences to better reflect source data. We automatically generate a synthetic dataset of positive and negative revisions by corrupting supported sentences and learn to revise reference sentences with contrastive learning. The intensity of revisions is treated as a controllable attribute so that, at inference, diverse candidates can be over-generated-then-rescored to balance faithfulness and abstraction. To test our methods, we extract noisy references from publicly available MIMIC-III discharge summaries for the task of hospital-course summarization, and vary the data on which models are trained. According to metrics and human evaluation, models trained on revised clinical references are much more faithful, informative, and fluent than models trained on original or filtered data.