# LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction

arXiv: https://arxiv.org/abs/2610.10138 · HTML: https://mlsanity.com/paper/2610.10138/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 17 of 17)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [Quantifying Long-Term Scientific Impact](https://mlsanity.com/paper/1306.3293/) (2013)
- [From Words to Worth: Newborn Article Impact Prediction with LLM](https://mlsanity.com/paper/2408.03934/) (2024)
- [Predicting the Citations of Scholarly Paper](https://mlsanity.com/paper/2008.05013/) (2020)
- [Longitudinal Citation Prediction using Temporal Graph Neural Networks](https://mlsanity.com/paper/2012.05742/) (2020)
- [Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction](https://mlsanity.com/paper/2305.17417/) (2023)
- [Predicting citation impact of research papers using GPT and other text embeddings](https://mlsanity.com/paper/2407.19942/) (2024)
- [H2CGL: Modeling Dynamics of Citation Network for Impact Prediction](https://mlsanity.com/paper/2305.01572/) (2023)
- [Measure the Impact of Institution and Paper via Institution-citation Network](https://mlsanity.com/paper/2008.04647/) (2020)
- [Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement](https://mlsanity.com/paper/2311.09262/) (2023)
- [SciEvo: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis](https://mlsanity.com/paper/2410.09510/) (2024)

## Abstract (arXiv)

Predicting the future impact of a newly published paper is challenging because it must be inferred from heterogeneous evidence available at publication time. Existing approaches often rely on a single source of information or combine multiple sources without accounting for their different predictive roles. In this paper, we present LLM4Impact, an evidence-aware method for scientific impact prediction that learns to represent, integrate, and calibrate heterogeneous information. LLM4Impact combines semantic, graph, LLM, and temporal representations, and injects graph information into a frozen LLM through continuous prefix tokens. A context aware gating mechanism adaptively weights different evidence, while a separate calibration module accounts for domain and temporal variation in citation scales. We further construct a large-scale benchmark dataset with 2 million papers, leakage-safe point-in-time heterogeneous ego graphs, temporal splits, and both year-level and month-level citation targets. Experiments show that LLM4Impact consistently outperforms strong semantic, graph, and LLM based baselines, with a 10.13% reduction in year RMSE on the in distribution test set and a 6.87% reduction under out-of-domain distribution. Our results reveal that the value of such evidence is context dependent: different papers benefit from different sources, while domain and publication time affect how evidence translates into citations. This finding motivates adaptive evidence selection and context-conditioned calibration rather than simply richer representations. We will release our code, benchmark, and an interactive web demonstration upon publication.