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

arXiv 2604.01379•105926049b83325a475bf485adbe53165b953e36faee19661b96ec9a62179a02
abstraction-paradoxagentic-systemsauthor-metadatabenchmarkco-authorshipdata-leakagedeanonymizationlink-predictionllmmulti-agentprivacyprompt-engineering-limitationssocial-networks

Paper metadata

arXiv ID
2604.01379
Version
Not specified by this published record
Category
Computer Science — Social and Information Networks (cs.SI)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_si
Record identifier
105926049b83325a475bf485adbe53165b953e36faee19661b96ec9a62179a02
Enrichment time
2026-04-03T08:52:21Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

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