Skip to content

CiteFuncRanker: an LLM-based pairwise ranking framework for multi-functional citation analysis

Aug 2026 · Scientometrics · Vol 131, pp. 6729 - 6750 · 0 citations · 50 references

TL;DR

CiteFuncRanker establishes a robust and interpretable ranking-based paradigm for bibliometric research by capturing the nuanced and context-dependent relative preferences between citation roles, and advance citation analysis beyond categorical classification toward a more context-aware and semantically grounded understanding of scholarly communication.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles

Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper's contribution. We introduce contribution-based credit scoring for research articles: a structured citation analysis that decomposes a paper's credit between its ow...

Sana Ebrahimi, Suraj Shetiya, Abolfazl Asudeh · 0 citations
Review Open access Aug 2026

A Joint Multi-Task Learning Framework for Citation Intent and Citation Evaluation Classification

Abstract Purpose This study aims to improve fine-grained understanding of citation contexts in scientific literature by jointly modeling two complementary aspects of citation behavior: citation intent and citation evaluation. Design/methodology/approach We propose a joint multi-task learning (Joint-MTL) framework that...

Yang Zhao, Guangyin Zhang · 0 citations
Open access Sep 2026

A Ranking Framework of Scientific Publications Using Temporal and Lexical Relevance and Citation Behavior

The results show that combining temporal, lexical relevance, and self-citation signals produces publication rankings that consistently differ from traditional citation- and recency-based methods while providing interpretable approach for examining multiple aspects of scientific publications.

A. Khatoon, Tehmina Amjad · 0 citations
Open access Aug 2026

Predicting Scholarly Impact with Temporal Preference Alignment

Impact-DPO integrates temporally informed prompting with direct preference optimization, enabling LLMs to learn comparative influence patterns without explicit graph message passing, and formalizes citation forecasting as pairwise preference learning on temporal text-attributed graphs.

Parham Hamouni, Ebrahim Bagheri · 0 citations
#large language models Open access Sep 2026

SciRep: A Ranking-Aware Representation Model for Scientific Text

Results demonstrate that the proposed ranking-aware distillation mechanism significantly enhances scientific text representation quality while maintaining efficient inference, offering a more effective contrastive learning method for domain-specific retrieval tasks.

Bing-Hao Fu, Jun Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.