Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ningrum, Panggih Kusuma, Mayr, Philipp, Smirnova, Nina, Atanassova, Iana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917981400858624
author Ningrum, Panggih Kusuma
Mayr, Philipp
Smirnova, Nina
Atanassova, Iana
author_facet Ningrum, Panggih Kusuma
Mayr, Philipp
Smirnova, Nina
Atanassova, Iana
contents UnScientify, a system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique to identify verbally expressed uncertainty in scientific texts and their authorial references. The core methodology of UnScientify is based on a multi-faceted pipeline that integrates span pattern matching, complex sentence analysis and author reference checking. This approach streamlines the labeling and annotation processes essential for identifying scientific uncertainty, covering a variety of uncertainty expression types to support diverse applications including information retrieval, text mining and scientific document processing. The evaluation results highlight the trade-offs between modern large language models (LLMs) and the UnScientify system. UnScientify, which employs more traditional techniques, achieved superior performance in the scientific uncertainty detection task, attaining an accuracy score of 0.808. This finding underscores the continued relevance and efficiency of UnScientify's simple rule-based and pattern matching strategy for this specific application. The results demonstrate that in scenarios where resource efficiency, interpretability, and domain-specific adaptability are critical, traditional methods can still offer significant advantages.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches
Ningrum, Panggih Kusuma
Mayr, Philipp
Smirnova, Nina
Atanassova, Iana
Computation and Language
Artificial Intelligence
Digital Libraries
UnScientify, a system designed to detect scientific uncertainty in scholarly full text. The system utilizes a weakly supervised technique to identify verbally expressed uncertainty in scientific texts and their authorial references. The core methodology of UnScientify is based on a multi-faceted pipeline that integrates span pattern matching, complex sentence analysis and author reference checking. This approach streamlines the labeling and annotation processes essential for identifying scientific uncertainty, covering a variety of uncertainty expression types to support diverse applications including information retrieval, text mining and scientific document processing. The evaluation results highlight the trade-offs between modern large language models (LLMs) and the UnScientify system. UnScientify, which employs more traditional techniques, achieved superior performance in the scientific uncertainty detection task, attaining an accuracy score of 0.808. This finding underscores the continued relevance and efficiency of UnScientify's simple rule-based and pattern matching strategy for this specific application. The results demonstrate that in scenarios where resource efficiency, interpretability, and domain-specific adaptability are critical, traditional methods can still offer significant advantages.
title Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches
topic Computation and Language
Artificial Intelligence
Digital Libraries
url https://arxiv.org/abs/2503.11376