# Beyond Text: Characterizing Domain Expert Needs in Document Research

arXiv: https://arxiv.org/abs/2504.12495 · HTML: https://mlsanity.com/paper/2504.12495/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 81 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [LASER: LLM Agent with State-Space Exploration for Web Navigation](https://mlsanity.com/paper/2309.08172/) (2023)
- [Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering](https://mlsanity.com/paper/1911.03868/) (2019)
- [Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking](https://mlsanity.com/paper/2410.03703/) (2024)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [Few-Shot Named Entity Recognition: A Comprehensive Study](https://mlsanity.com/paper/2012.14978/) (2020)
- [Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols](https://mlsanity.com/paper/2009.14237/) (2020)
- [Stereotype or Personalization? User Identity Biases Chatbot Recommendations](https://mlsanity.com/paper/2410.05613/) (2024)
- [A Survey on Contextualised Semantic Shift Detection](https://mlsanity.com/paper/2304.01666/) (2023)
- [AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters](https://mlsanity.com/paper/2401.06408/) (2024)
- [AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation](https://mlsanity.com/paper/2404.12753/) (2024)
- [Few-shot Learning for Named Entity Recognition in Medical Text](https://mlsanity.com/paper/1811.05468/) (2018)
- [CitationIE: Leveraging the Citation Graph for Scientific Information Extraction](https://mlsanity.com/paper/2106.01560/) (2021)
- [Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature](https://mlsanity.com/paper/2408.15836/) (2024)
- [Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval](https://mlsanity.com/paper/2410.23214/) (2024)
- [Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications](https://mlsanity.com/paper/2212.09676/) (2022)
- [NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval](https://mlsanity.com/paper/2310.14282/) (2023)
- [Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research](https://mlsanity.com/paper/2104.07874/) (2021)
- [Anchor Prediction: Automatic Refinement of Internet Links](https://mlsanity.com/paper/2305.14337/) (2023)
- [Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?](https://mlsanity.com/paper/2502.07963/) (2025)

## Built on by (most cited first, 1 of 1)

- [FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction](https://mlsanity.com/paper/2510.20926/) (2025)

## Abstract (arXiv)

Working with documents is a key part of almost any knowledge work, from contextualizing research in a literature review to reviewing legal precedent. Recently, as their capabilities have expanded, primarily text-based NLP systems have often been billed as able to assist or even automate this kind of work. But to what extent are these systems able to model these tasks as experts conceptualize and perform them now? In this study, we interview sixteen domain experts across two domains to understand their processes of document research, and compare it to the current state of NLP systems. We find that our participants processes are idiosyncratic, iterative, and rely extensively on the social context of a document in addition its content; existing approaches in NLP and adjacent fields that explicitly center the document as an object, rather than as merely a container for text, tend to better reflect our participants' priorities, though they are often less accessible outside their research communities. We call on the NLP community to more carefully consider the role of the document in building useful tools that are accessible, personalizable, iterative, and socially aware.