COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
Unsupervised Domain Clusters in Pretrained Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Introduces the first interpersonal emotion dataset from congressional tweets and demonstrates that joint neural modeling of interpersonal group relationships and emotions yields performance gains on both.
citing papers explorer
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.