G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.
Newsweeder: Learning to filter netnews, 1995
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
G-Loss: Graph-Guided Fine-Tuning of Language Models
G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.