Papers with general-domain baselines
MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | a new framework for domain adaptation of text embedding models addresses the challenges of adapting general-domain text embeds to specialized domains. |
| Approach: | They propose a framework for domain adaptation of text embedding models that integrates masked supervision and mangled objectives within a unified training pipeline. |
| Outcome: | The proposed framework improves on high-resource and low-resourced domains while preserving the robustness of the original model. |