Year: 2026
Type: conference-paper
Abstract: The rapid growth of scientific literature calls for automated methods to assess and predict research impact.Prior work has largely focused on citation-based metrics, leaving limited evaluation of models' capability to reason about other impact dimensions.To this end, we introduce SCIIMPACT, a large-scale, multi-dimensional benchmark for scientific impact prediction spanning 19 fields.SCIIM-PACT captures various forms of scientific influence, ranging from citation counts to award recognition, media attention, patent reference, and artifact adoption, by integrating heterogeneous data sources and targeted web crawling.It comprises 215,928 contrastive paper pairs reflecting meaningful impact differences in both short-(e.g., Best Paper Award) and long-term settings (e.g., Nobel Prize).We evaluate 11 widely used large language models (LLMs) on SCIIMPACT.Results show that off-the-shelf models show substantial variability across dimensions and fields, while multitask supervised fine-tuning consistently enables smaller LLMs (e.g., 4B) to markedly outperform much larger models (e.g., 30B) and surpass powerful closed-source LLMs (e.g., o4-mini).These results establish SCIIM-PACT as a challenging benchmark and demonstrate its value for multi-dimensional, multifield scientific impact prediction.Our project homepage is https
Authors: Hangxiao Zhu, Yuyu Zhang, Ping Nie, Yu Zhang
Institutions: Texas A&M University, University of Waterloo
Language: English
Subfield: Statistics, Probability and Uncertainty
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7166827432