aiqbench analysis
ClinicalAligner26AM addresses a critical gap in specialized NLP by introducing a cross-lingual aligner optimized for biomedical and clinical domains, outperforming existing models in annotation projection tasks. The system leverages optimal transport techniques to distill a sharpened alignment matrix, achieving top-tier F1 scores across six languages in the MultiClinCorpus shared task. This approach offers a robust solution for teams requiring high-fidelity translation auditing and entity mapping in low-resource medical contexts.
ClinicalAligner26AM: A Cross-Lingual Aligner for Dataset Translation; Evidences from the MultiClinCorpus Shared Task
arXiv:2606.08673v1 Announce Type: new Abstract: Word-level cross-lingual alignment is central to annotation projection, translation auditing, and cross-lingual faithfulness estimation, yet existing neural aligners are rarely adapted to specialized domains. In this paper, we introduce ClinicalAligner26AM, a large-context multilingual aligner model for biomedical and clinical text initialized from ClinicalEncoder26AM. Our training recipe is inspired by AWESoME Align. We build our soft alignment target by sharpening with Sinkhorn-Knop optimal transport a cost matrix established for parallel clinical texts and conversations through the fusion of sentence-level, phrase-level, and token-level signals. We distill this sharpened alignment matrix directly into our student aligner, by encouraging its naive cosine-based token similarity scores to match this target. At inference time, we project source-span scores through the learned token alignment matrix and decode the longest valid high-scoring span in the target text, optionally supported by MultiClinNER predictions summarized in Appendix B. We evaluate CA26AM on the MultiClinCorpus shared task, which projects Spanish clinical entity annotations into six target languages. Our two submitted systems ranked respectively first and second across all languages and entity types, with character-weighted F1 scores above 0.95 in nearly all settings.
Abstract:Word-level cross-lingual alignment is central to annotation projection, translation auditing, and cross-lingual faithfulness estimation, yet existing neural aligners are rarely adapted to specialized domains. In this paper, we introduce ClinicalAligner26AM, a large-context multilingual aligner model for biomedical and clinical text initialized from ClinicalEncoder26AM. Our training recipe is inspired by AWESoME Align. We build our soft alignment target by sharpening with Sinkhorn-Knop optimal transport a cost matrix established for parallel clinical texts and conversations through the fusion of sentence-level, phrase-level, and token-level signals. We distill this sharpened alignment matrix directly into our student aligner, by encouraging its naive cosine-based token similarity scores to match this target. At inference time, we project source-span scores through the learned token alignment matrix and decode the longest valid high-scoring span in the target text, optionally supported by MultiClinNER predictions summarized in Appendix B. We evaluate CA26AM on the MultiClinCorpus shared task, which projects Spanish clinical entity annotations into six target languages. Our two submitted systems ranked respectively first and second across all languages and entity types, with character-weighted F1 scores above 0.95 in nearly all settings.
Computation and Language (cs.CL)
arXiv:2606.08673 [cs.CL]
(or arXiv:2606.08673v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.08673 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 276 words
Related coverage
LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish
arXiv · Jul 28, 2026
BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR
arXiv · Sep 9, 2026
Tiny Aya in the wild: What people are building with open multilingual AI
Cohere · Jul 14, 2026
Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment $\unicode{x2013}$ Is English Enough?
arXiv · Aug 6, 2026