@inproceedings{singh-etal-2025-information,
title = "An Information-Theoretic Approach to Reducing Fertility in {LLM}s for {M}anipuri Machine Translation",
author = "Singh, Telem Joyson and
Sanasam, Ranbir Singh and
Sarmah, Priyankoo",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.145/",
pages = "2394--2404",
ISBN = "979-8-89176-303-6",
abstract = "Large language models (LLMs) have transformed machine translation, yet they have a high subword fertility issue for low-resource languages, which leads to slow inference speed and increased costs. While vocabulary expansion via continual pre-training is a common solution, it often degrades translation quality and requires large target-language corpora, which are unavailable for truly low-resource languages. To address this, we investigate tokenization efficiency through an information-theoretic lens, building on the established hypothesis that word length correlates with information content. From this perspective, we characterize tokenization inefficiency as having high fertility for low-information (highly predictable) words. Guided by this principle, we introduce a novel fine-tuning strategy that systematically identifies informationally redundant words{---}those with high fertility but low information content{---}for targeted vocabulary expansion and model fine-tuning. Experiments fine-tuning BLOOM and LLaMA-3 in English-Manipuri and other two language pairs show that our proposed method significantly reduces fertility by 50{\%} and accelerates inference by more than 2 times, without compromising and often exceeding the translation quality of standard LLM baselines, providing a theoretically grounded solution for efficient LLM-based MT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2025-information">
<titleInfo>
<title>An Information-Theoretic Approach to Reducing Fertility in LLMs for Manipuri Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Telem</namePart>
<namePart type="given">Joyson</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ranbir</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Sanasam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyankoo</namePart>
<namePart type="family">Sarmah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have transformed machine translation, yet they have a high subword fertility issue for low-resource languages, which leads to slow inference speed and increased costs. While vocabulary expansion via continual pre-training is a common solution, it often degrades translation quality and requires large target-language corpora, which are unavailable for truly low-resource languages. To address this, we investigate tokenization efficiency through an information-theoretic lens, building on the established hypothesis that word length correlates with information content. From this perspective, we characterize tokenization inefficiency as having high fertility for low-information (highly predictable) words. Guided by this principle, we introduce a novel fine-tuning strategy that systematically identifies informationally redundant words—those with high fertility but low information content—for targeted vocabulary expansion and model fine-tuning. Experiments fine-tuning BLOOM and LLaMA-3 in English-Manipuri and other two language pairs show that our proposed method significantly reduces fertility by 50% and accelerates inference by more than 2 times, without compromising and often exceeding the translation quality of standard LLM baselines, providing a theoretically grounded solution for efficient LLM-based MT.</abstract>
<identifier type="citekey">singh-etal-2025-information</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.145/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2394</start>
<end>2404</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Information-Theoretic Approach to Reducing Fertility in LLMs for Manipuri Machine Translation
%A Singh, Telem Joyson
%A Sanasam, Ranbir Singh
%A Sarmah, Priyankoo
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F singh-etal-2025-information
%X Large language models (LLMs) have transformed machine translation, yet they have a high subword fertility issue for low-resource languages, which leads to slow inference speed and increased costs. While vocabulary expansion via continual pre-training is a common solution, it often degrades translation quality and requires large target-language corpora, which are unavailable for truly low-resource languages. To address this, we investigate tokenization efficiency through an information-theoretic lens, building on the established hypothesis that word length correlates with information content. From this perspective, we characterize tokenization inefficiency as having high fertility for low-information (highly predictable) words. Guided by this principle, we introduce a novel fine-tuning strategy that systematically identifies informationally redundant words—those with high fertility but low information content—for targeted vocabulary expansion and model fine-tuning. Experiments fine-tuning BLOOM and LLaMA-3 in English-Manipuri and other two language pairs show that our proposed method significantly reduces fertility by 50% and accelerates inference by more than 2 times, without compromising and often exceeding the translation quality of standard LLM baselines, providing a theoretically grounded solution for efficient LLM-based MT.
%U https://aclanthology.org/2025.findings-ijcnlp.145/
%P 2394-2404
Markdown (Informal)
[An Information-Theoretic Approach to Reducing Fertility in LLMs for Manipuri Machine Translation](https://aclanthology.org/2025.findings-ijcnlp.145/) (Singh et al., Findings 2025)
ACL
- Telem Joyson Singh, Ranbir Singh Sanasam, and Priyankoo Sarmah. 2025. An Information-Theoretic Approach to Reducing Fertility in LLMs for Manipuri Machine Translation. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2394–2404, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.