Introduces Indi-RomCoM benchmark for evaluating LLMs on Romanized code-mixed Indic-English instructions across seven tasks, four languages, and three mixing levels.
InFind- ings of the Association for Computational Linguistics: ACL 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3verdicts
UNVERDICTED 3representative citing papers
A MoE speech projector with language expert groups, language-specific and load-balancing losses, and multi-stage training with a transition loss improves code-switching speech translation by 0.86 BLEU and 0.93 COMET on average over SeamlessM4T.
A survey that unifies prior code-switching research for LLMs into a taxonomy of data, modeling, and evaluation and distills it into actionable recommendations for practitioners.
citing papers explorer
-
Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions
Introduces Indi-RomCoM benchmark for evaluating LLMs on Romanized code-mixed Indic-English instructions across seven tasks, four languages, and three mixing levels.
-
Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment
A MoE speech projector with language expert groups, language-specific and load-balancing losses, and multi-stage training with a transition loss improves code-switching speech translation by 0.86 BLEU and 0.93 COMET on average over SeamlessM4T.
-
Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs
A survey that unifies prior code-switching research for LLMs into a taxonomy of data, modeling, and evaluation and distills it into actionable recommendations for practitioners.