Intermediate-task training effects on zero-shot cross-lingual CLIP performance in MMMU across language families

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tas

Research goal: How does intermediate-task training on English visual-question-answering datasets affect the zero-shot cross-lingual performance of CLIP-based models on the MMMU benchmark when evaluated across different language families (e.g., Indo-European vs. Sino-Tibetan)?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.