Saved in:
Bibliographic Details
Main Authors: Hull, Gavin, Bihlo, Alex
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.08941
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908362596155392
author Hull, Gavin
Bihlo, Alex
author_facet Hull, Gavin
Bihlo, Alex
contents Predicting the future citation rates of academic papers is an important step toward the automation of research evaluation and the acceleration of scientific progress. We present $\textbf{ForeCite}$, a simple but powerful framework to append pre-trained causal language models with a linear head for average monthly citation rate prediction. Adapting transformers for regression tasks, ForeCite achieves a test correlation of $ρ= 0.826$ on a curated dataset of 900K+ biomedical papers published between 2000 and 2024, a 27-point improvement over the previous state-of-the-art. Comprehensive scaling-law analysis reveals consistent gains across model sizes and data volumes, while temporal holdout experiments confirm practical robustness. Gradient-based saliency heatmaps suggest a potentially undue reliance on titles and abstract texts. These results establish a new state-of-the-art in forecasting the long-term influence of academic research and lay the groundwork for the automated, high-fidelity evaluation of scientific contributions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08941
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ForeCite: Adapting Pre-Trained Language Models to Predict Future Citation Rates of Academic Papers
Hull, Gavin
Bihlo, Alex
Machine Learning
Computation and Language
Predicting the future citation rates of academic papers is an important step toward the automation of research evaluation and the acceleration of scientific progress. We present $\textbf{ForeCite}$, a simple but powerful framework to append pre-trained causal language models with a linear head for average monthly citation rate prediction. Adapting transformers for regression tasks, ForeCite achieves a test correlation of $ρ= 0.826$ on a curated dataset of 900K+ biomedical papers published between 2000 and 2024, a 27-point improvement over the previous state-of-the-art. Comprehensive scaling-law analysis reveals consistent gains across model sizes and data volumes, while temporal holdout experiments confirm practical robustness. Gradient-based saliency heatmaps suggest a potentially undue reliance on titles and abstract texts. These results establish a new state-of-the-art in forecasting the long-term influence of academic research and lay the groundwork for the automated, high-fidelity evaluation of scientific contributions.
title ForeCite: Adapting Pre-Trained Language Models to Predict Future Citation Rates of Academic Papers
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2505.08941