# Knowledge Pull Requests for Continual Document Authoring

arXiv: https://arxiv.org/abs/2609.26634 · HTML: https://mlsanity.com/paper/2609.26634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [FRUIT: Faithfully Reflecting Updated Information in Text](https://mlsanity.com/paper/2112.08634/) (2021)
- [NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge](https://mlsanity.com/paper/2206.07106/) (2022)
- [AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees](https://mlsanity.com/paper/2404.08417/) (2024)
- [Auto-ARGUE: LLM-Based Report Generation Evaluation](https://mlsanity.com/paper/2509.26184/) (2025)
- [MegaWika: Millions of reports and their sources across 50 diverse languages](https://mlsanity.com/paper/2307.07049/) (2023)
- [LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2507.05346/) (2025)
- [WINELL: Wikipedia Never-Ending Updating with LLM Agents](https://mlsanity.com/paper/2508.03728/) (2025)
- [Overview of the TREC 2025 RAGTIME Track](https://mlsanity.com/paper/2602.10024/) (2026)
- [MegaWika 2: A More Comprehensive Multilingual Collection of Articles and their Sources](https://mlsanity.com/paper/2508.03828/) (2025)

## Abstract (arXiv)

We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge changed or regenerate from scratch. A KPR integrates new knowledge into a document by extracting claims, filtering and routing them to sections, and flagging conflicts with existing content, producing a ChangeLog that separates what knowledge changes (claim proposal) from how the text changes (document diff). We evaluate KPRs on revising Wikipedia across languages and updating query-driven reports on RAGTIME. KPRs integrate more information and better preserve existing content than rewriting from sources or regenerating from scratch, while adding the most information per token generated. A KPR-revised article also grounds question answering better than a frontier model with search, which does not surface knowledge documented only in other languages.