@inproceedings{castello-2026-enhancing,
title = "Enhancing {LLM} Translation Performance for {S}panish{--}{V}alencian through Supervised Fine-Tuning and Reinforcement Learning",
author = "Castell{\'o}, Paula Guerrero",
editor = "Shterionov, Dimitar and
Vanmassenhove, Eva and
De Sisto, Mirella and
Blain, Fred and
Pourmostafa Roshan Sharami, Javad and
Lepp, Lisa and
Manna, Chiara and
Rescigno, Argentina Anna and
Karakanta, Alina and
Rigouts Terryn, Ayla and
Lardelli, Manuel and
Resende, Natalia and
Murgolo, Elena and
Hackenbuchner, Jani{\c{c}}a and
Zaretskaya, Anna and
Espl{\`a}-Gomis, Miquel and
Etchegoyhen, Thierry and
Gromann, Dagmar and
Bawden, Rachel and
Haddow, Barry and
Szoc, Sara and
Forcada, Mikel and
Moniz, Helena",
booktitle = "Proceedings of the 26th Annual Conference of the {E}uropean Association for Machine Translation (Volume 2)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-2.27/",
pages = "72--79",
ISBN = "9789403901404",
abstract = "Valencian, the Western Catalan variety used in the Valencian Community of Spain, lacks a dedicated language code in most multilingual machine translation (MT) systems, and is systematically rendered closer to the standard written Eastern Catalan used in Catalonia. We address this gap by adapting TranslateGemma-4B-IT, a 4-billion-parameter instruction-tuned (IT) large language model (LLM) specialized for translation, via three post-training strategies using only public corpora and Quantized Low-Rank Adaptation (QLoRA): (i) supervised fine-tuning (SFT); (ii) Group Relative Policy Optimization (GRPO), a reinforcement learning (RL) technique, with chrF plus a naturalness reward (GRPOV1); and (iii) GRPO with a composite automatic-metric reward (GRPOV2). Our results suggest that reward-function alignment with the target dialect is a key determinant of RL success in low-resource dialectal MT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castello-2026-enhancing">
<titleInfo>
<title>Enhancing LLM Translation Performance for Spanish–Valencian through Supervised Fine-Tuning and Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="given">Guerrero</namePart>
<namePart type="family">Castelló</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">De Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Lepp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Argentina</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Rescigno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="family">Rigouts Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Lardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Resende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiça</namePart>
<namePart type="family">Hackenbuchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tilburg, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">9789403901404</identifier>
</relatedItem>
<abstract>Valencian, the Western Catalan variety used in the Valencian Community of Spain, lacks a dedicated language code in most multilingual machine translation (MT) systems, and is systematically rendered closer to the standard written Eastern Catalan used in Catalonia. We address this gap by adapting TranslateGemma-4B-IT, a 4-billion-parameter instruction-tuned (IT) large language model (LLM) specialized for translation, via three post-training strategies using only public corpora and Quantized Low-Rank Adaptation (QLoRA): (i) supervised fine-tuning (SFT); (ii) Group Relative Policy Optimization (GRPO), a reinforcement learning (RL) technique, with chrF plus a naturalness reward (GRPOV1); and (iii) GRPO with a composite automatic-metric reward (GRPOV2). Our results suggest that reward-function alignment with the target dialect is a key determinant of RL success in low-resource dialectal MT.</abstract>
<identifier type="citekey">castello-2026-enhancing</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-2.27/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>72</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing LLM Translation Performance for Spanish–Valencian through Supervised Fine-Tuning and Reinforcement Learning
%A Castelló, Paula Guerrero
%Y Shterionov, Dimitar
%Y Vanmassenhove, Eva
%Y De Sisto, Mirella
%Y Blain, Fred
%Y Pourmostafa Roshan Sharami, Javad
%Y Lepp, Lisa
%Y Manna, Chiara
%Y Rescigno, Argentina Anna
%Y Karakanta, Alina
%Y Rigouts Terryn, Ayla
%Y Lardelli, Manuel
%Y Resende, Natalia
%Y Murgolo, Elena
%Y Hackenbuchner, Janiça
%Y Zaretskaya, Anna
%Y Esplà-Gomis, Miquel
%Y Etchegoyhen, Thierry
%Y Gromann, Dagmar
%Y Bawden, Rachel
%Y Haddow, Barry
%Y Szoc, Sara
%Y Forcada, Mikel
%Y Moniz, Helena
%S Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901404
%F castello-2026-enhancing
%X Valencian, the Western Catalan variety used in the Valencian Community of Spain, lacks a dedicated language code in most multilingual machine translation (MT) systems, and is systematically rendered closer to the standard written Eastern Catalan used in Catalonia. We address this gap by adapting TranslateGemma-4B-IT, a 4-billion-parameter instruction-tuned (IT) large language model (LLM) specialized for translation, via three post-training strategies using only public corpora and Quantized Low-Rank Adaptation (QLoRA): (i) supervised fine-tuning (SFT); (ii) Group Relative Policy Optimization (GRPO), a reinforcement learning (RL) technique, with chrF plus a naturalness reward (GRPOV1); and (iii) GRPO with a composite automatic-metric reward (GRPOV2). Our results suggest that reward-function alignment with the target dialect is a key determinant of RL success in low-resource dialectal MT.
%U https://aclanthology.org/2026.eamt-2.27/
%P 72-79
Markdown (Informal)
[Enhancing LLM Translation Performance for Spanish–Valencian through Supervised Fine-Tuning and Reinforcement Learning](https://aclanthology.org/2026.eamt-2.27/) (Castelló, EAMT 2026)
ACL