Exploring LLMs for Scientific Information Extraction Using The SciEx Framework

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Sha, Sadekar, Ayush, Self, Nathan, Su, Yiqi, Andersland, Lars, Chaplin, Mira, Zhang, Annabel, Yang, Hyoju, Henderson, James B, Wigginton, Krista, Marr, Linsey, Murali, T. M., Ramakrishnan, Naren
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908783095054336
author Li, Sha
Sadekar, Ayush
Self, Nathan
Su, Yiqi
Andersland, Lars
Chaplin, Mira
Zhang, Annabel
Yang, Hyoju
Henderson, James B
Wigginton, Krista
Marr, Linsey
Murali, T. M.
Ramakrishnan, Naren
author_facet Li, Sha
Sadekar, Ayush
Self, Nathan
Su, Yiqi
Andersland, Lars
Chaplin, Mira
Zhang, Annabel
Yang, Hyoju
Henderson, James B
Wigginton, Krista
Marr, Linsey
Murali, T. M.
Ramakrishnan, Naren
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
Li, Sha
Sadekar, Ayush
Self, Nathan
Su, Yiqi
Andersland, Lars
Chaplin, Mira
Zhang, Annabel
Yang, Hyoju
Henderson, James B
Wigginton, Krista
Marr, Linsey
Murali, T. M.
Ramakrishnan, Naren
Artificial Intelligence
Computation and Language
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.
title Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2512.10004