CRISP: Characterizing Relative Impact of Scholarly Publications
For researchers and bibliometric analysts, CRISP provides a more accurate and efficient way to assess citation impact by leveraging full citation context.
CRISP introduces a joint ranking method for cited papers within a citing paper using LLMs, achieving +9.5% accuracy and +8.3% F1 over prior state-of-the-art on a human-annotated dataset.
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 CRISP, 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. CRISP outperforms a prior state-of-the-art impact classifier by +9.5% accuracy and +8.3% F1 on a dataset of human-annotated citations. CRISP 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.