# Exploring LLMs for Scientific Information Extraction Using The SciEx Framework

arXiv: https://arxiv.org/abs/2512.10004 · HTML: https://mlsanity.com/paper/2512.10004/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 10 Dec 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction](https://mlsanity.com/paper/2010.09885/) (2020)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [VisText: A Benchmark for Semantically Rich Chart Captioning](https://mlsanity.com/paper/2307.05356/) (2023)
- [Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering](https://mlsanity.com/paper/2303.05352/) (2023)
- [SciCap: Generating Captions for Scientific Figures](https://mlsanity.com/paper/2110.11624/) (2021)
- [OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition](https://mlsanity.com/paper/2403.19128/) (2024)
- [Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion](https://mlsanity.com/paper/2501.17887/) (2025)
- [Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols](https://mlsanity.com/paper/2009.14237/) (2020)
- [SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning](https://mlsanity.com/paper/2306.03491/) (2023)
- [Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature](https://mlsanity.com/paper/2411.03484/) (2024)

## Built on by (most cited first, 4 of 4)

- [Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining](https://mlsanity.com/paper/2605.04278/) (2026)
- [IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction](https://mlsanity.com/paper/2606.18181/) (2026)
- [PEARL: Auditable Repair for Scientific Reasoning Graph Extraction](https://mlsanity.com/paper/2607.17917/) (2026)
- [LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data](https://mlsanity.com/paper/2608.27629/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly touted as powerful tools for automating scientific information extraction. However, existing methods and tools often struggle with the realities of scientific literature: long-context documents, multi-modal content, and reconciling varied and inconsistent fine-grained information across multiple publications into standardized formats. These challenges are further compounded when the desired data schema or extraction ontology changes rapidly, making it difficult to re-architect or fine-tune existing systems. We present SciEx, a modular and composable framework that decouples key components including PDF parsing, multi-modal retrieval, extraction, and aggregation. This design streamlines on-demand data extraction while enabling extensibility and flexible integration of new models, prompting strategies, and reasoning mechanisms. We evaluate SciEx on datasets spanning three scientific topics for its ability to extract fine-grained information accurately and consistently. Our findings provide practical insights into both the strengths and limitations of current LLM-based pipelines.