# From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale

arXiv: https://arxiv.org/abs/2504.13834 · HTML: https://mlsanity.com/paper/2504.13834/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 67 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 29 of 29)

- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [The Geometry of Categorical and Hierarchical Concepts in Large Language Models](https://mlsanity.com/paper/2406.01506/) (2024)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Accelerating Innovation Through Analogy Mining](https://mlsanity.com/paper/1706.05585/) (2017)
- [Language Models as Hierarchy Encoders](https://mlsanity.com/paper/2401.11374/) (2024)
- [TnT-LLM: Text Mining at Scale with Large Language Models](https://mlsanity.com/paper/2403.12173/) (2024)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [A Computational Inflection for Scientific Discovery](https://mlsanity.com/paper/2205.02007/) (2022)
- [Constructing Taxonomies from Pretrained Language Models](https://mlsanity.com/paper/2010.12813/) (2020)
- [Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction](https://mlsanity.com/paper/2309.01715/) (2023)
- [Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature](https://mlsanity.com/paper/2408.15836/) (2024)
- [Taxonomy Tree Generation from Citation Graph](https://mlsanity.com/paper/2410.03761/) (2024)
- [CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts](https://mlsanity.com/paper/2408.09070/) (2024)
- [Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction](https://mlsanity.com/paper/2202.04876/) (2022)
- [A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion](https://mlsanity.com/paper/2402.13405/) (2024)
- [Generate FAIR Literature Surveys with Scholarly Knowledge Graphs](https://mlsanity.com/paper/2006.01747/) (2020)
- [NLPContributions: An Annotation Scheme for Machine Reading of Scholarly Contributions in Natural Language Processing Literature](https://mlsanity.com/paper/2006.12870/) (2020)
- [Automatic Bottom-Up Taxonomy Construction: A Software Application Domain Study](https://mlsanity.com/paper/2409.15881/) (2024)
- [Creating a Fine Grained Entity Type Taxonomy Using LLMs](https://mlsanity.com/paper/2402.12557/) (2024)
- [FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models](https://mlsanity.com/paper/2402.13623/) (2024)
- [Probing Pretrained Language Models with Hierarchy Properties](https://mlsanity.com/paper/2312.09670/) (2023)
- [The Ontoverse: Democratising Access to Knowledge Graph-based Data Through a Cartographic Interface](https://mlsanity.com/paper/2408.03339/) (2024)
- [OpenForge: Probabilistic Metadata Integration](https://mlsanity.com/paper/2412.09788/) (2024)

## Built on by (most cited first, 8 of 8)

- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases](https://mlsanity.com/paper/2505.20321/) (2025)
- [SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models](https://mlsanity.com/paper/2605.00620/) (2026)
- [An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation](https://mlsanity.com/paper/2608.07023/) (2026)
- [AutoPDEBench: Benchmarking LLM Auto-Research for Neural PDE Solver Design](https://mlsanity.com/paper/2609.32245/) (2026)

## Abstract (arXiv)

Scientific knowledge is growing rapidly, making it difficult to track progress and high-level conceptual links across broad disciplines. While tools like citation networks and search engines help retrieve related papers, they lack the abstraction needed to capture the density and structure of activity across subfields. We motivate the goal of organizing broad swaths of scientific literature into a high-quality hierarchical structure that spans multiple levels of abstraction---from broad domains to specific studies. Such a representation can provide insights into which fields are well-explored and which are under-explored. To achieve this goal, we develop a hybrid approach that combines efficient embedding-based clustering with LLM-based prompting, striking a balance between scalability and semantic precision. Compared to LLM-heavy methods like iterative tree construction, our approach achieves superior quality-speed trade-offs. Our hierarchies capture different dimensions of research contributions, reflecting the interdisciplinary and multifaceted nature of modern science. We evaluate its utility by measuring how effectively an LLM-based agent can navigate the hierarchy to locate target papers. Results show that our method improves interpretability and offers an alternative pathway for exploring scientific literature beyond traditional search methods. Code, data and demo are available: https://github.com/JHU-CLSP/science-hierarchography