Impact of SWIM-IR Synthetic Data Fine-Tuning on Cross-Lingual Retrieval Performance in the XTYLE Benchmark

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data for training is often scarcely available. In this paper, rather than using more cross-lingual data for training, we propose to use cross-lingual query generation to augment passage representations with queries in languages other than the original passage language. These augmented representations are used at inference time so that the representation can enco

Research goal: How does fine-tuning multilingual dense retrieval models with SWIM-IR synthetic data affect performance on cross-lingual retrieval tasks in the XTYLE benchmark compared to models trained only on Wikipedia data?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.