# Can LLMs Predict Academic Collaboration? Topology Heuristics vs. LLM-Based Link Prediction on Real Co-authorship Networks

arXiv: https://arxiv.org/abs/2604.01379 · HTML: https://mlsanity.com/paper/2604.01379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Predicting Race and Ethnicity From the Sequence of Characters in a Name](https://mlsanity.com/paper/1805.02109/) (2018)
- [Large-scale comparison of bibliographic data sources: Scopus, Web of Science, Dimensions, Crossref, and Microsoft Academic](https://mlsanity.com/paper/2005.10732/) (2020)

## Abstract (arXiv)

Can large language models (LLMs) predict which researchers will collaborate? We study this question through link prediction on real-world co-authorship networks from OpenAlex (9.96M authors, 108.7M edges), evaluating whether LLMs can predict future scientific collaborations using only author profiles, without access to graph structure. Using Qwen2.5-72B-Instruct across three historical eras of AI research, we find that LLMs and topology heuristics capture distinct signals and are strongest in complementary settings. On new-edge prediction under natural class imbalance, the LLM achieves AUROC 0.714--0.789, outperforming Common Neighbors, Jaccard, and Preferential Attachment, with recall up to 92.9%; under balanced evaluation, the LLM outperforms all topology heuristics in every era (AUROC 0.601--0.658 vs. best-heuristic 0.525--0.538); on continued edges, the LLM (0.687) is competitive with Adamic-Adar (0.684). Critically, 78.6--82.7% of new collaborations occur between authors with no common neighbor -- a blind spot where all topology heuristics score zero but the LLM still achieves AUROC 0.652 by reasoning from author metadata alone. A temporal metadata ablation reveals that research concepts are the dominant signal (removing concepts drops AUROC by 0.047--0.084). Providing pre-computed graph features to the LLM degrades performance due to anchoring effects, confirming that LLMs and topology methods should operate as separate, complementary channels. A socio-cultural ablation finds that name-inferred ethnicity and institutional country do not predict collaboration beyond topology, reflecting the demographic homogeneity of AI research. A node2vec baseline achieves AUROC comparable to Adamic-Adar, establishing that LLMs access a fundamentally different information channel -- author metadata -- rather than encoding the same structural signal differently.