@inproceedings{marmonier-etal-2025-explicit,
title = "Explicit Learning and the {LLM} in Machine Translation",
author = "Marmonier, Malik and
Bawden, Rachel and
Sagot, Beno{\^i}t",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1599/",
doi = "10.18653/v1/2025.emnlp-main.1599",
pages = "31372--31422",
ISBN = "979-8-89176-332-6",
abstract = "This study explores an LLM{'}s ability to learn new languages using explanations found in a grammar book{---}a process we term ``explicit learning.'' To rigorously assess this ability, we design controlled translation experiments between English and constructed languages generated{---}through specific cryptographic means{---}from Latin or French. Contrary to previous studies, our results demonstrate that LLMs do possess a measurable capacity for explicit learning. This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases. Supervised fine-tuning on ad hoc chains of thought significantly enhances LLM performance but struggles to generalize to typologically novel or more complex linguistic features. These findings point to the need for more diverse training sets and alternative fine-tuning strategies to further improve explicit learning by LLMs, benefiting low-resource languages typically described in grammar books but lacking extensive corpora."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marmonier-etal-2025-explicit">
<titleInfo>
<title>Explicit Learning and the LLM in Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malik</namePart>
<namePart type="family">Marmonier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</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">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>This study explores an LLM’s ability to learn new languages using explanations found in a grammar book—a process we term “explicit learning.” To rigorously assess this ability, we design controlled translation experiments between English and constructed languages generated—through specific cryptographic means—from Latin or French. Contrary to previous studies, our results demonstrate that LLMs do possess a measurable capacity for explicit learning. This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases. Supervised fine-tuning on ad hoc chains of thought significantly enhances LLM performance but struggles to generalize to typologically novel or more complex linguistic features. These findings point to the need for more diverse training sets and alternative fine-tuning strategies to further improve explicit learning by LLMs, benefiting low-resource languages typically described in grammar books but lacking extensive corpora.</abstract>
<identifier type="citekey">marmonier-etal-2025-explicit</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1599</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1599/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>31372</start>
<end>31422</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explicit Learning and the LLM in Machine Translation
%A Marmonier, Malik
%A Bawden, Rachel
%A Sagot, Benoît
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F marmonier-etal-2025-explicit
%X This study explores an LLM’s ability to learn new languages using explanations found in a grammar book—a process we term “explicit learning.” To rigorously assess this ability, we design controlled translation experiments between English and constructed languages generated—through specific cryptographic means—from Latin or French. Contrary to previous studies, our results demonstrate that LLMs do possess a measurable capacity for explicit learning. This ability, however, diminishes as the complexity of the linguistic phenomena to be learned increases. Supervised fine-tuning on ad hoc chains of thought significantly enhances LLM performance but struggles to generalize to typologically novel or more complex linguistic features. These findings point to the need for more diverse training sets and alternative fine-tuning strategies to further improve explicit learning by LLMs, benefiting low-resource languages typically described in grammar books but lacking extensive corpora.
%R 10.18653/v1/2025.emnlp-main.1599
%U https://aclanthology.org/2025.emnlp-main.1599/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1599
%P 31372-31422
Markdown (Informal)
[Explicit Learning and the LLM in Machine Translation](https://aclanthology.org/2025.emnlp-main.1599/) (Marmonier et al., EMNLP 2025)
ACL
- Malik Marmonier, Rachel Bawden, and Benoît Sagot. 2025. Explicit Learning and the LLM in Machine Translation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 31372–31422, Suzhou, China. Association for Computational Linguistics.