# A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents

arXiv: https://arxiv.org/abs/2305.14772 · HTML: https://mlsanity.com/paper/2305.14772/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 71 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents](https://mlsanity.com/paper/2305.14564/) (2023)
- [Explaining Relationships Between Scientific Documents](https://mlsanity.com/paper/2002.00317/) (2020)
- [QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines](https://mlsanity.com/paper/2010.02815/) (2020)
- [Inquisitive Question Generation for High Level Text Comprehension](https://mlsanity.com/paper/2010.01657/) (2020)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting](https://mlsanity.com/paper/2107.00414/) (2021)
- [Scim: Intelligent Skimming Support for Scientific Papers](https://mlsanity.com/paper/2205.04561/) (2022)
- [Relatedly: Scaffolding Literature Reviews with Existing Related Work Sections](https://mlsanity.com/paper/2302.06754/) (2023)
- [Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model](https://mlsanity.com/paper/2210.02498/) (2022)
- [Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections](https://mlsanity.com/paper/2111.00701/) (2021)
- [QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions](https://mlsanity.com/paper/2109.12655/) (2021)
- [Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification](https://mlsanity.com/paper/1804.11254/) (2018)
- [Elaborative Simplification as Implicit Questions Under Discussion](https://mlsanity.com/paper/2305.10387/) (2023)
- [Conversations with Documents. An Exploration of Document-Centered Assistance](https://mlsanity.com/paper/2002.00747/) (2020)
- [Understanding Questions that Arise When Working with Business Documents](https://mlsanity.com/paper/2203.15073/) (2022)
- [Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge](https://mlsanity.com/paper/1705.08063/) (2017)
- [Hammer PDF: An Intelligent PDF Reader for Scientific Papers](https://mlsanity.com/paper/2204.02809/) (2022)

## Built on by (most cited first, 16 of 16)

- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2411.04075/) (2024)
- [DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation](https://mlsanity.com/paper/2412.13175/) (2024)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions](https://mlsanity.com/paper/2402.13551/) (2024)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models](https://mlsanity.com/paper/2410.22360/) (2024)
- [Which questions should I answer? Salience Prediction of Inquisitive Questions](https://mlsanity.com/paper/2404.10917/) (2024)
- [A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking](https://mlsanity.com/paper/2505.02171/) (2025)
- [QUDSELECT: Selective Decoding for Questions Under Discussion Parsing](https://mlsanity.com/paper/2408.01046/) (2024)
- [A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2608.24419/) (2026)
- [SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval](https://mlsanity.com/paper/2412.15443/) (2024)
- [GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation](https://mlsanity.com/paper/2409.15566/) (2024)
- [Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning](https://mlsanity.com/paper/2509.17921/) (2025)
- [Measuring and Reducing Unusable Replies of LLM Agents](https://mlsanity.com/paper/2610.19659/) (2026)

## Abstract (arXiv)

Many real-world applications (e.g., note taking, search) require extracting a sentence or paragraph from a document and showing that snippet to a human outside of the source document. Yet, users may find snippets difficult to understand as they lack context from the original document. In this work, we use language models to rewrite snippets from scientific documents to be read on their own. First, we define the requirements and challenges for this user-facing decontextualization task, such as clarifying where edits occur and handling references to other documents. Second, we propose a framework that decomposes the task into three stages: question generation, question answering, and rewriting. Using this framework, we collect gold decontextualizations from experienced scientific article readers. We then conduct a range of experiments across state-of-the-art commercial and open-source language models to identify how to best provide missing-but-relevant information to models for our task. Finally, we develop QaDecontext, a simple prompting strategy inspired by our framework that improves over end-to-end prompting. We conclude with analysis that finds, while rewriting is easy, question generation and answering remain challenging for today's models.