tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker

Andrei Tiberiu Carp


Abstract
Multiword expressions (MWEs), particularlyidioms, pose persistent challengesfor vision-language systems due to theirnon-compositional semantics and culturallygrounded meanings. This paper presentsGLIMMER, a three-stage hybrid ranking systemthat evaluates how well images expressthe intended meaning of MWEs across 15 languages.Our approach uses LLM-generatedsemantic glosses as multilingual meaning anchors,combined with dual-path embeddingscoring (textual captions and visual features),and LLM-based semantic verification. Evaluatedon the ADMIRE shared task benchmark,GLIMMER achieves competitive performanceacross diverse languages without relying onparallel training data or language-specific resources.The results show that using glossesto anchor meaning helps match idioms withimages across languages and modalities, andthat combining retrieval with reasoning is morerobust than using embeddings alone.
Anthology ID:
2026.mwe-1.23
Volume:
Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)
Month:
March
Year:
2026
Address:
Rabat, Marocco
Editors:
Atul Kr. Ojha, Verginica Barbu Mititelu, Mathieu Constant, Ivelina Stoyanova, A. Seza Doğruöz, Alexandre Rademaker
Venues:
MWE | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
170–176
Language:
URL:
https://aclanthology.org/2026.mwe-1.23/
DOI:
Bibkey:
Cite (ACL):
Andrei Tiberiu Carp. 2026. tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker. In Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026), pages 170–176, Rabat, Marocco. Association for Computational Linguistics.
Cite (Informal):
tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker (Carp, MWE 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.mwe-1.23.pdf