A two-stage cited text span recognition model based on LLM-driven data augmentation and contrastive learning
Bibliographic Data
| ID | 21441850 |
|---|---|
| Authors | Mingxing Han (0000-0001-9342-8062, Nanjing University), Shiyan Ou (0000-0001-8617-6987, Nanjing University, corresponding author), Jie Li (0000-0002-5131-4769, Nanjing University), Jiaxuan Li (0000-0003-0902-9750), Kunhao Zhu (Nanjing University), Weimin Nie (Nanjing University) |
| Year | 2026 |
| Volume | 131 |
| Issue | 5 |
| Pages | 2857-2883 |
| Publication date | 2026-05-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Scientometrics (JOURNAL) |
| Journal identifiers | ISSN: 0138-9130 • E-ISSN: 1588-2861 |
| Publisher | Springer Science and Business Media LLC (PUBLISHER) |
| DOI | 10.1007/s11192-026-05606-0 |
| OpenAlex | W7153568405 |
| Language | EN |
| References cited | 30 |
Deep learning · Feature (linguistics) · Rationality · Span (engineering) · Stability (learning theory) · Task (project management) · Task Analysis · Academic integrity and plagiarism · Authorship Attribution and Profiling · Text Readability and Simplification
SciBert
Sentence-Bert
Smote
Academic literature recommendation in large-scale citation networks enhanced by large language models
Cited text span identification for scientific summarisation using pre-trained encoders
Examining knowledge entities and its relationships based on citation sentences using a multi-anchor bipartite network
Type/Token Ratios
Referencing as Persuasion
| Highly cited | No |
|---|