# Building astroBERT, a language model for Astronomy & Astrophysics

arXiv: https://arxiv.org/abs/2112.00590 · HTML: https://mlsanity.com/paper/2112.00590/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 2 of 2)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)

## Built on by (most cited first, 19 of 19)

- [A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery](https://mlsanity.com/paper/2406.10833/) (2024)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [AstroLLaMA: Towards Specialized Foundation Models in Astronomy](https://mlsanity.com/paper/2309.06126/) (2023)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [An Interdisciplinary Outlook on Large Language Models for Scientific Research](https://mlsanity.com/paper/2311.04929/) (2023)
- [Tracing the Development of the Virtual Particle Concept Using Semantic Change Detection](https://mlsanity.com/paper/2410.16855/) (2024)
- [Meaning at the Planck scale? Contextualized word embeddings for doing history, philosophy, and sociology of science](https://mlsanity.com/paper/2411.14073/) (2024)
- [FeynTune: Large Language Models for High-Energy Theory](https://mlsanity.com/paper/2508.03716/) (2025)
- [Detecting Entities in the Astrophysics Literature: A Comparison of Word-based and Span-based Entity Recognition Methods](https://mlsanity.com/paper/2211.13819/) (2022)
- [NASA Science Mission Directorate Knowledge Graph Discovery](https://mlsanity.com/paper/2303.10871/) (2023)
- [Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics](https://mlsanity.com/paper/2411.14877/) (2024)
- [Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference](https://mlsanity.com/paper/2407.17663/) (2024)
- [Searching for Carriers of the Diffuse Interstellar Bands Across Disciplines, using Natural Language Processing](https://mlsanity.com/paper/2211.08513/) (2022)
- [Identifying Planetary Names in Astronomy Papers: A Multi-Step Approach](https://mlsanity.com/paper/2312.08579/) (2023)
- [Psychological Assessments with Large Language Models: A Privacy-Focused and Cost-Effective Approach](https://mlsanity.com/paper/2402.03435/) (2024)
- [AstroReview: An LLM-driven Multi-Agent Framework for Telescope Proposal Peer Review and Refinement](https://mlsanity.com/paper/2512.24754/) (2025)
- [AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics](https://mlsanity.com/paper/2604.02156/) (2026)
- [Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking](https://mlsanity.com/paper/2609.24246/) (2026)
- [Local Citation Recommendation Without Graph Signals](https://mlsanity.com/paper/2610.15832/) (2026)

## Abstract (arXiv)

The existing search tools for exploring the NASA Astrophysics Data System (ADS) can be quite rich and empowering (e.g., similar and trending operators), but researchers are not yet allowed to fully leverage semantic search. For example, a query for "results from the Planck mission" should be able to distinguish between all the various meanings of Planck (person, mission, constant, institutions and more) without further clarification from the user. At ADS, we are applying modern machine learning and natural language processing techniques to our dataset of recent astronomy publications to train astroBERT, a deeply contextual language model based on research at Google. Using astroBERT, we aim to enrich the ADS dataset and improve its discoverability, and in particular we are developing our own named entity recognition tool. We present here our preliminary results and lessons learned.