ARISE bootstraps rules from syntactic n-grams and LLM-generated synthetic data, reporting consistent text-classification gains over baselines.
In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10513– 10529, Bangkok, Thailand
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
-
ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification
ARISE bootstraps rules from syntactic n-grams and LLM-generated synthetic data, reporting consistent text-classification gains over baselines.