Crystal: Characterizing Relative Impact of Scholarly Publications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Collison, Hannah, Van Durme, Benjamin, Khashabi, Daniel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915951416442880
author Collison, Hannah
Van Durme, Benjamin
Khashabi, Daniel
author_facet Collison, Hannah
Van Durme, Benjamin
Khashabi, Daniel
contents Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper. While this focuses on the most directly relevant text, it prevents relative comparisons across all the works a paper cites. We propose Crystal, which instead jointly ranks all cited papers within a citing paper using large language models (LLMs). To mitigate LLMs' positional bias, we rank each list three times in a randomized order and aggregate the impact labels through majority voting. This joint approach leverages the full citation context, rather than evaluating citations independently, to more reliably distinguish impactful references. Crystal outperforms a prior state-of-the-art impact classifier by +9.5% accuracy and +8.3% F1 on a dataset of human-annotated citations. Crystal further gains efficiency through fewer LLM calls and performs competitively with an open-source model, enabling scalable, cost-effective citation impact analysis. We release our rankings, impact labels, and codebase to support future research.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26791
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Crystal: Characterizing Relative Impact of Scholarly Publications
Collison, Hannah
Van Durme, Benjamin
Khashabi, Daniel
Digital Libraries
Artificial Intelligence
Computation and Language
Computers and Society
Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper. While this focuses on the most directly relevant text, it prevents relative comparisons across all the works a paper cites. We propose Crystal, which instead jointly ranks all cited papers within a citing paper using large language models (LLMs). To mitigate LLMs' positional bias, we rank each list three times in a randomized order and aggregate the impact labels through majority voting. This joint approach leverages the full citation context, rather than evaluating citations independently, to more reliably distinguish impactful references. Crystal outperforms a prior state-of-the-art impact classifier by +9.5% accuracy and +8.3% F1 on a dataset of human-annotated citations. Crystal further gains efficiency through fewer LLM calls and performs competitively with an open-source model, enabling scalable, cost-effective citation impact analysis. We release our rankings, impact labels, and codebase to support future research.
title Crystal: Characterizing Relative Impact of Scholarly Publications
topic Digital Libraries
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2603.26791