Bagging-Based Model Merging for Robust General Text Embeddings
General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage broad generalization. However, it remains unclear how different multi-task training strategies compare in practice, and how to efficiently adapt embedding models as new domains and data types continually emerge. In this work, we present a systematic study of multi-task training for text embeddings from two perspectives: data scheduling and model merging. We compare batch-level shuffling, sequential training variants, two-stage training, and multiple merging granularities, and find that simple batch-level shuffli...
| Authors | Hengran Zhang, Keping Bi, Jiafeng Guo et al. |
|---|---|
| Primary category | cs.IR |
| Published | 5 February 2026 |
| Last updated at source | 9 February 2026 |
Connected in the knowledge graph
- ICT-TIME-and-Querit/BOOM_4B_v1Model · cited by
- ICT-TIME-and-Querit/BOOM-v1.5-training-dataDataset · cited by
- ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1Model · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.