LocRegen: Cost-Efficient Redundancy Removal in Multilingual E-commerce Titles with Small Language Models

Bryan Zhang, Stephan Walter, Luca Lomanto, Merve Arinik


Abstract
E-commerce product titles often include redundant information that negatively impacts the user experience. Removing repeated words through restructuring and paraphrasing can make titles more concise and improve readability. While large language models can optimize titles, their computational cost makes them impractical for large-scale applications. In this paper, we first analyze the sources of repetition in multilingual product titles, then present LocRegen, a system that uses smaller language models to efficiently remove redundancies while preserving essential product attributes. Our experiments across five languages show that LocRegen with a 7B model substantially outperforms a 47B mixture-of-experts model: LocRegen achieves a 2.4% redundant title rate compared to 3.5% for the 47B model, and maintains a 3.8% overall error rate across all error categories including key product attribute omission compared to 8.4% for the 47B model. These results demonstrate that LocRegen delivers superior performance on cost-effective hardware with acceptable latency, making it practical for large-scale deployment where much larger models would be computationally prohibitive.
Anthology ID:
2026.eamt-1.33
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
528–537
Language:
URL:
https://aclanthology.org/2026.eamt-1.33/
DOI:
Bibkey:
Cite (ACL):
Bryan Zhang, Stephan Walter, Luca Lomanto, and Merve Arinik. 2026. LocRegen: Cost-Efficient Redundancy Removal in Multilingual E-commerce Titles with Small Language Models. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 528–537, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
LocRegen: Cost-Efficient Redundancy Removal in Multilingual E-commerce Titles with Small Language Models (Zhang et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.33.pdf