从引用到贡献：大模型辅助的研究论文贡献度评分
文章背景与核心概要
传统的学术引用指标通常将所有引用平等对待，忽视了先前工作在研究论文发展过程中所扮演的不同角色。本文提出了一种基于贡献度的学术文章信用评分框架，能够将一篇论文的学术价值在其原创贡献与所依赖的基础文献之间进行拆解分配。
该框架的核心亮点包括：受合作博弈论启发的“贡献树”分层模型、利用大语言模型（LLM）作为可扩展的噪声比较估计器来确定局部文档重要性，以及通过加权引用图将模型扩展至语料库级别以计算更广泛的学术贡献和归一化影响力得分。
📌 摘要与核心亮点
传统的科学影响力基于引用衡量指标通常将引用视为统一的信号，忽略了被引用的工作在论文贡献中所起的不同作用。我们为研究文章引入了一种基于贡献度的信用评分机制：这是一种结构化的引用分析方法，可将论文的学术价值拆解为其自身的原创贡献与所依赖的前期工作。受科学信用的合作博弈论视角的启发，我们提出了“贡献树（contribution tree）”这一分层框架，它能够在文档结构中保持重要性的守恒，并将原创贡献与引用衍生的贡献区分开来。为了使该框架具备可扩展性，我们利用大模型作为局部重要性的噪声比较估计器。我们进一步通过在加权引用图上推进贡献传播，将该模型扩展到文章集合，从而得出语料库级别的贡献和归一化影响力得分。我们的实验表明，该框架能够捕捉到超越表面启发式方法的贡献信号。
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 own original contribution and the prior work it builds on. Motivated by a cooperative-game view of scientific credit, we propose the contribution tree, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores. Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics.
📖 原文摘要
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 own original contribution and the prior work it builds on. Motivated by a cooperative-game view of scientific credit, we propose the contribution tree, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores. Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics.
🏷️ 元数据与附加信息
- 主要分类: 数字图书馆 (
cs.DL) - 次要分类: 人工智能 (
cs.AI)、计算与语言 (cs.CL)、信息检索 (cs.IR) - 代码仓库: GitHub - Importance_Scoring