Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
Not on the map. Why?
Abstract (arXiv)
Despite the central importance of research papers to scientific progress, they can be difficult to read. Comprehension is often stymied when the information needed to understand a passage resides somewhere else: in another section, or in another paper. In this work, we envision how interfaces can bring definitions of technical terms and symbols to readers when and where they need them most. We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols. A usability study showed that the tool helps researchers of all experience levels read papers. Furthermore, researchers were eager to have ScholarPhi's definitions available to support their everyday reading.
Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Sep 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 6; 2023: 10; 2024: 7; 2025: 8; 2026: 3.
36 papers.
Sort:
By area:
- 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Reviewcited by 37
- 2022Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processingcited by 23
- 2022A Computational Inflection for Scientific Discoverycited by 22
- 2023Beyond Summarization: Designing AI Support for Real-World Expository Writing Taskscited by 20
- 2024PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Paperscited by 18
- 2022Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publicationscited by 14
- 2023Personalized Jargon Identification for Enhanced Interdisciplinary Communicationcited by 11
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
- 2025Federated Retrieval Augmented Generation for Multi-Product Question Answeringcited by 10
- 2023The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfacescited by 9
- 2024Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistancecited by 8
- 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
24 more
- 2023CARE: Collaborative AI-Assisted Reading Environmentcited by 7
- 2024Steering AI-Driven Personalization of Scientific Text for General Audiencescited by 7
- 2021PAWLS: PDF Annotation With Labels and Structurecited by 4
- 2022Longtonotes: OntoNotes with Longer Coreference Chainscited by 4
- 2025Exploring LLMs for Scientific Information Extraction Using The SciEx Frameworkcited by 4
- 2023S2abEL: A Dataset for Entity Linking from Scientific Tablescited by 3
- 2024SciDaSynth: Interactive Structured Data Extraction from Scientific Literature with Large Language Modelcited by 3
- 2024STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsingcited by 3
- 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answerscited by 3
- 2025Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Workcited by 2
- 2022Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Papercited by 1
- 2023How Data Scientists Review the Scholarly Literaturecited by 1
- 2023Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extractioncited by 1
- 2023From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Contextcited by 1
- 2025Beyond Text: Characterizing Domain Expert Needs in Document Researchcited by 1
- 2025Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generationcited by 1
- 2025TreeReader: A Hierarchical Academic Paper Reader Powered by Language Modelscited by 1
- 2026Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitationcited by 1
- 2021A system for information extraction from scientific texts in Russiancited by 0
- 2023Envisioning the Next-Gen Document Readercited by 0
- 2023Extracting Definienda in Mathematical Scholarly Articles with Transformerscited by 0
- 2024RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Modelscited by 0
- 2026Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responsescited by 0
- 2026ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cuescited by 0
- 2026Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses5 Jun 2026
- 2026ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues4 May 2026
- 2026Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitation25 Mar 2026
- 2025Exploring LLMs for Scientific Information Extraction Using The SciEx Framework10 Dec 2025
- 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers1 Oct 2025
- 2025TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models25 Jul 2025
- 2025Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation26 Apr 2025
- 2025Beyond Text: Characterizing Domain Expert Needs in Document Research16 Apr 2025
- 2025Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work24 Mar 2025
- 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems3 Mar 2025
- 2025Federated Retrieval Augmented Generation for Multi-Product Question Answering25 Jan 2025
- 2024Steering AI-Driven Personalization of Scientific Text for General Audiences15 Nov 2024
24 more
- 2024STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing1 Nov 2024
- 2024Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance6 Sep 2024
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration1 Aug 2024
- 2024RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models28 May 2024
- 2024SciDaSynth: Interactive Structured Data Extraction from Scientific Literature with Large Language Model21 Apr 2024
- 2024PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers5 Mar 2024
- 2023Extracting Definienda in Mathematical Scholarly Articles with Transformers21 Nov 2023
- 2023Personalized Jargon Identification for Enhanced Interdisciplinary Communication16 Nov 2023
- 2023From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context6 Oct 2023
- 2023Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction24 May 2023
- 2023S2abEL: A Dataset for Entity Linking from Scientific Tables30 Apr 2023
- 2023Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks5 Apr 2023
- 2023The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces25 Mar 2023
- 2023CARE: Collaborative AI-Assisted Reading Environment24 Feb 2023
- 2023Envisioning the Next-Gen Document Reader15 Feb 2023
- 2023How Data Scientists Review the Scholarly Literature10 Jan 2023
- 2022Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications19 Dec 2022
- 2022Longtonotes: OntoNotes with Longer Coreference Chains7 Oct 2022
- 2022Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper22 Sep 2022
- 2022A Computational Inflection for Scientific Discovery4 May 2022
- 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review22 Apr 2022
- 2022Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing28 Feb 2022
- 2021A system for information extraction from scientific texts in Russian14 Sep 2021
- 2021PAWLS: PDF Annotation With Labels and Structure25 Jan 2021
- 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Reviewcited by 37
- 2022Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processingcited by 23
- 2022A Computational Inflection for Scientific Discoverycited by 22
- 2023Beyond Summarization: Designing AI Support for Real-World Expository Writing Taskscited by 20
- 2024PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Paperscited by 18
- 2022Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publicationscited by 14
- 2023Personalized Jargon Identification for Enhanced Interdisciplinary Communicationcited by 11
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Explorationcited by 10
- 2023The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfacescited by 9
- 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
- 2023CARE: Collaborative AI-Assisted Reading Environmentcited by 7
- 2024Steering AI-Driven Personalization of Scientific Text for General Audiencescited by 7
12 most cited of 32 All 32 (JSON)
- 2026Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses5 Jun 2026
- 2026ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues4 May 2026
- 2026Robust Multilingual Text-to-Pictogram Mapping for Scalable Reading Rehabilitation25 Mar 2026
- 2025Exploring LLMs for Scientific Information Extraction Using The SciEx Framework10 Dec 2025
- 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers1 Oct 2025
- 2025TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models25 Jul 2025
- 2025Beyond Text: Characterizing Domain Expert Needs in Document Research16 Apr 2025
- 2025Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work24 Mar 2025
- 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems3 Mar 2025
- 2024Steering AI-Driven Personalization of Scientific Text for General Audiences15 Nov 2024
- 2024DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration1 Aug 2024
- 2024RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models28 May 2024
12 newest of 32 All 32 (JSON)