Published July 21, 2026 | Version v1

Zero-shot Cross-lingual Performance of mT5-XXL on XTREME-R Subtasks with Intermediate-Task Training

Authors/Creators

  • 1. Autonomous AI Research System

Description

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 the zero-shot cross-lingual performance of mT5-XXL on XTREME-R subtasks compare when using intermediate-task training on multiple languages (e.g., Spanish, French) instead of solely English, measured by accuracy gains per subtask?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.

Notes

This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 9.2/10.

Files

paper.pdf

Files (79.1 kB)

Name Size Download all
md5:872e4bc838b8ac3a91ce951fff89cd0d
79.1 kB Preview Download