# SALSA: Semi-Autonomous Literature Summarization Assistant

arXiv: https://arxiv.org/abs/2609.22210 · HTML: https://mlsanity.com/paper/2609.22210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering](https://mlsanity.com/paper/2303.05352/) (2023)
- [Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references](https://mlsanity.com/paper/1402.4578/) (2014)
- [Artificial intelligence to automate the systematic review of scientific literature](https://mlsanity.com/paper/2401.10917/) (2024)
- [ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining](https://mlsanity.com/paper/2402.12993/) (2024)
- [Context-Aware Chart Element Detection](https://mlsanity.com/paper/2305.04151/) (2023)
- [Plot2Spectra: an Automatic Spectra Extraction Tool](https://mlsanity.com/paper/2107.02827/) (2021)
- [LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation](https://mlsanity.com/paper/2305.01837/) (2023)
- [Review of the state of the art in autonomous artificial intelligence](https://mlsanity.com/paper/2210.10659/) (2022)
- [Rethinking the production and publication of machine-reusable expressions of research findings](https://mlsanity.com/paper/2405.13129/) (2024)
- [Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy](https://mlsanity.com/paper/2606.00065/) (2026)

## Abstract (arXiv)

SALSA (Semi-Autonomous Literature Summarization Assistant) is an open- source, human-in-the-loop platform for extracting structured scientific datasets from multimodal literature sources. The software combines document parsing, large language models, optical character recognition, computer vision, figure digitization, and user-guided correction tools to recover structured information from text, tables, figures, and captions. Users can configure extraction stages, define dataset schemas, perform interventions on digitized figures, and export verified data for downstream analysis and machine learning. SALSA is designed to automate repetitive literature curation tasks while preserving oversight where expert judgment is required. By supporting customizable extraction workflows across diverse input types, the software provides a flexible framework for scalable, reliable data curation for materials research, and potentially across several disciplines. Users are responsible for ensuring that all inputs, extraction workflows, and downstream uses comply with applicable publisher agreements, copyright and licensing terms, institutional policies, and data-use requirements.