# Mapping Scientific Literature with Large Language Models and Topic Modeling

arXiv: https://arxiv.org/abs/2510.16152 · HTML: https://mlsanity.com/paper/2510.16152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 88 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [Scientific Large Language Models: A Survey on Biological & Chemical Domains](https://mlsanity.com/paper/2401.14656/) (2024)
- [Automated Lay Language Summarization of Biomedical Scientific Reviews](https://mlsanity.com/paper/2012.12573/) (2020)
- [Explaining How Transformers Use Context to Build Predictions](https://mlsanity.com/paper/2305.12535/) (2023)
- [Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing](https://mlsanity.com/paper/2203.00130/) (2022)
- [A Survey on Neural Topic Models: Methods, Applications, and Challenges](https://mlsanity.com/paper/2401.15351/) (2024)
- [Personalized Jargon Identification for Enhanced Interdisciplinary Communication](https://mlsanity.com/paper/2311.09481/) (2023)
- [On the rise of fear speech in online social media](https://mlsanity.com/paper/2303.10311/) (2023)
- [From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science](https://mlsanity.com/paper/2405.00706/) (2024)
- [Feature analysis of multidisciplinary scientific collaboration patterns based on PNAS](https://mlsanity.com/paper/1706.05858/) (2017)
- [Nature, Science, and PNAS -- Disciplinary profiles and impact](https://mlsanity.com/paper/2008.04721/) (2020)
- [Moving Beyond LDA: A Comparison of Unsupervised Topic Modelling Techniques for Qualitative Data Analysis of Online Communities](https://mlsanity.com/paper/2412.14486/) (2024)
- [SciTopic: Enhancing Topic Discovery in Scientific Literature through Advanced LLM](https://mlsanity.com/paper/2508.20514/) (2025)

## Abstract (arXiv)

Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science. This study introduces a large language model (LLM)-driven framework for mapping scientific literature from a topic modeling perspective. The approach is demonstrated on a 20-year corpus of more than 1,500 engineering-related articles published in the Proceedings of the National Academy of Sciences (PNAS). A two-stage classification pipeline first assigns a primary thematic category to each article based on its abstract, followed by full-text analysis to identify secondary classifications that reveal latent cross-topic connections within the corpus. Unlike conventional topic models, the LLM-based framework produces semantically interpretable topics while maintaining strong quantitative performance. Comparative evaluation against established topic modeling methods shows higher topic diversity and lower overlap with competitive coherence metrics. Manual validation on a randomly sampled subset of abstracts yields an accuracy of 75.9%. Additional traditional natural language processing analyses confirm that the generated topics correspond to meaningful linguistic patterns in the corpus. A bipartite network linking primary and secondary classifications further reveals implicit thematic relationships that are not readily observable through abstracts or keyword systems alone. The findings indicate that the framework independently recovers much of the journal's editorial dual-classification structure without prior knowledge of its schema. Overall, the proposed approach offers a powerful tool for mapping science and identifying emerging cross-topic connections in research.