Japanese SLM dialect robustness correlates with base LLM robustness; both dialectal training data and speech-encoder fine-tuning raise SLM robustness.
Assessing Thai Di- alect Performance in LLMs with Automatic Benchmarks and Human Evaluation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models
Japanese SLM dialect robustness correlates with base LLM robustness; both dialectal training data and speech-encoder fine-tuning raise SLM robustness.