# On Improving Summarization Factual Consistency from Natural Language Feedback

arXiv: https://arxiv.org/abs/2212.09968 · HTML: https://mlsanity.com/paper/2212.09968/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 52 of its 69 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 52)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [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)
- [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)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (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)
- [Factual Error Correction for Abstractive Summarization Models](https://mlsanity.com/paper/2010.08712/) (2020)
- [Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors](https://mlsanity.com/paper/2205.12854/) (2022)
- [Encode, Tag, Realize: High-Precision Text Editing](https://mlsanity.com/paper/1909.01187/) (2019)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)

## Built on by (most cited first, 30 of 38)

- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [Shepherd: A Critic for Language Model Generation](https://mlsanity.com/paper/2308.04592/) (2023)
- [On Learning to Summarize with Large Language Models as References](https://mlsanity.com/paper/2305.14239/) (2023)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge](https://mlsanity.com/paper/2305.08281/) (2023)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews](https://mlsanity.com/paper/2306.12587/) (2023)
- [Learning to Refine with Fine-Grained Natural Language Feedback](https://mlsanity.com/paper/2407.02397/) (2024)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [The Impact of Imperfect XAI on Human-AI Decision-Making](https://mlsanity.com/paper/2307.13566/) (2023)
- [Reasons to Reject? Aligning Language Models with Judgments](https://mlsanity.com/paper/2312.14591/) (2023)
- [Localizing Factual Inconsistencies in Attributable Text Generation](https://mlsanity.com/paper/2410.07473/) (2024)
- [Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges](https://mlsanity.com/paper/2401.08664/) (2023)
- [Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios](https://mlsanity.com/paper/2305.14987/) (2023)
- [GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence](https://mlsanity.com/paper/2402.12566/) (2024)
- [AmbigNLG: Addressing Task Ambiguity in Instruction for NLG](https://mlsanity.com/paper/2402.17717/) (2024)
- [MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration](https://mlsanity.com/paper/2503.15272/) (2025)
- [XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates](https://mlsanity.com/paper/2309.11063/) (2023)
- [Improving Factual Consistency of News Summarization by Contrastive Preference Optimization](https://mlsanity.com/paper/2310.19347/) (2023)
- [Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning](https://mlsanity.com/paper/2406.00303/) (2024)
- [Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization](https://mlsanity.com/paper/2507.02145/) (2025)
- [USB: A Unified Summarization Benchmark Across Tasks and Domains](https://mlsanity.com/paper/2305.14296/) (2023)
- [The Critique of Critique](https://mlsanity.com/paper/2401.04518/) (2024)
- [Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy](https://mlsanity.com/paper/2402.12821/) (2024)
- [Personalized Abstractive Summarization by Tri-agent Generation Pipeline](https://mlsanity.com/paper/2305.02483/) (2023)
- [P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models](https://mlsanity.com/paper/2311.09741/) (2023)
- [Learning to Verify Summary Facts with Fine-Grained LLM Feedback](https://mlsanity.com/paper/2412.10689/) (2024)
- [ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback](https://mlsanity.com/paper/2503.21332/) (2025)
- [RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.10448/) (2025)

## Abstract (arXiv)

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and user preference alignment. To this end, we consider factual consistency in summarization, the quality that the summary should only contain information supported by the input documents, as the user-expected preference. We collect a high-quality dataset, DeFacto, containing human demonstrations and informational natural language feedback consisting of corrective instructions, edited summaries, and explanations with respect to the factual consistency of the summary. Using our dataset, we study three natural language generation tasks: (1) editing a summary by following the human feedback, (2) generating human feedback for editing the original summary, and (3) revising the initial summary to correct factual errors by generating both the human feedback and edited summary. We show that DeFacto can provide factually consistent human-edited summaries and further insights into summarization factual consistency thanks to its informational natural language feedback. We further demonstrate that fine-tuned language models can leverage our dataset to improve the summary factual consistency, while large language models lack the zero-shot learning ability in our proposed tasks that require controllable text generation.