@inproceedings{balal-gungor-2026-diversity,
title = "Diversity-Aware Literary Machine Translation with Multi-Reward Policy Optimization",
author = {Balal, Zeynep Yirmibe{\c{s}}o{\u{g}}lu and
G{\"u}ng{\"o}r, Tunga},
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 1)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-1.17/",
pages = "231--244",
ISBN = "9789403901411",
abstract = "Literary translation is a difficult task that not only requires semantic accuracy but also stylistic richness and lexical diversity. Pretrained and supervised fine-tuned Large Language Models (LLMs) can over-rely on safe vocabulary choices, leading to translations that lack lexical variety. To address this problem, we propose a novel diversity-aware multi-objective Group Relative Policy Optimization (GRPO) framework that pushes the limits of open-source translation quality while increasing lexical diversity. We introduce two diversity-aware reward mechanisms, a Leave-One-Out (LOO) marginal contribution reward and a Self-BLEU penalty, balanced alongside neural quality metrics (COMET), lexical overlap (BLEU), and structural constraints. Through experiments on Turkish-English and German-English using Qwen3-14B, we show that our diversity-aware reinforcement learning approach successfully enhances lexical richness alongside translation quality. Our models achieve state-of-the-art open-source performance in literary translation, bridging the gap with leading commercial systems and demonstrating that policy optimization can effectively steer LLMs toward high-quality, lexically diverse outputs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balal-gungor-2026-diversity">
<titleInfo>
<title>Diversity-Aware Literary Machine Translation with Multi-Reward Policy Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zeynep</namePart>
<namePart type="given">Yirmibeşoğlu</namePart>
<namePart type="family">Balal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tunga</namePart>
<namePart type="family">Güngör</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 1)</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">9789403901411</identifier>
</relatedItem>
<abstract>Literary translation is a difficult task that not only requires semantic accuracy but also stylistic richness and lexical diversity. Pretrained and supervised fine-tuned Large Language Models (LLMs) can over-rely on safe vocabulary choices, leading to translations that lack lexical variety. To address this problem, we propose a novel diversity-aware multi-objective Group Relative Policy Optimization (GRPO) framework that pushes the limits of open-source translation quality while increasing lexical diversity. We introduce two diversity-aware reward mechanisms, a Leave-One-Out (LOO) marginal contribution reward and a Self-BLEU penalty, balanced alongside neural quality metrics (COMET), lexical overlap (BLEU), and structural constraints. Through experiments on Turkish-English and German-English using Qwen3-14B, we show that our diversity-aware reinforcement learning approach successfully enhances lexical richness alongside translation quality. Our models achieve state-of-the-art open-source performance in literary translation, bridging the gap with leading commercial systems and demonstrating that policy optimization can effectively steer LLMs toward high-quality, lexically diverse outputs.</abstract>
<identifier type="citekey">balal-gungor-2026-diversity</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.17/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>231</start>
<end>244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diversity-Aware Literary Machine Translation with Multi-Reward Policy Optimization
%A Balal, Zeynep Yirmibeşoğlu
%A Güngör, Tunga
%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 1)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901411
%F balal-gungor-2026-diversity
%X Literary translation is a difficult task that not only requires semantic accuracy but also stylistic richness and lexical diversity. Pretrained and supervised fine-tuned Large Language Models (LLMs) can over-rely on safe vocabulary choices, leading to translations that lack lexical variety. To address this problem, we propose a novel diversity-aware multi-objective Group Relative Policy Optimization (GRPO) framework that pushes the limits of open-source translation quality while increasing lexical diversity. We introduce two diversity-aware reward mechanisms, a Leave-One-Out (LOO) marginal contribution reward and a Self-BLEU penalty, balanced alongside neural quality metrics (COMET), lexical overlap (BLEU), and structural constraints. Through experiments on Turkish-English and German-English using Qwen3-14B, we show that our diversity-aware reinforcement learning approach successfully enhances lexical richness alongside translation quality. Our models achieve state-of-the-art open-source performance in literary translation, bridging the gap with leading commercial systems and demonstrating that policy optimization can effectively steer LLMs toward high-quality, lexically diverse outputs.
%U https://aclanthology.org/2026.eamt-1.17/
%P 231-244
Markdown (Informal)
[Diversity-Aware Literary Machine Translation with Multi-Reward Policy Optimization](https://aclanthology.org/2026.eamt-1.17/) (Balal & Güngör, EAMT 2026)
ACL