Using multiple LLM-generated summaries of the same abstract as positive pairs trains scientific text embeddings that beat citation-trained baselines on retrieval and clustering, while the new benchmark shares its training signal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
Using multiple LLM-generated summaries of the same abstract as positive pairs trains scientific text embeddings that beat citation-trained baselines on retrieval and clustering, while the new benchmark shares its training signal.