TriMix dynamically fuses logits from three model sources to outperform baselines and Proxy Tuning on eight low-resource languages across four model families.
MC ^2 : Towards Transparent and Culturally-Aware NLP for Minority Languages in C hina
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Introduces CHALIS benchmark dataset testing language ID on mutually intelligible cousin language pairs and orthographically noisy inputs, with evaluation showing existing systems struggle substantially.
Replacing tokens, freezing the corresponding embeddings, and tuning the rest of the model improves NLU performance on low-resource languages compared to full fine-tuning.
citing papers explorer
-
Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
TriMix dynamically fuses logits from three model sources to outperform baselines and Proxy Tuning on eight low-resource languages across four model families.
-
CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios
Introduces CHALIS benchmark dataset testing language ID on mutually intelligible cousin language pairs and orthographically noisy inputs, with evaluation showing existing systems struggle substantially.
-
Modular Monolingual Adaptation using Pretrained Language Models
Replacing tokens, freezing the corresponding embeddings, and tuning the rest of the model improves NLU performance on low-resource languages compared to full fine-tuning.