@inproceedings{naorem-etal-2026-shot,
title = "Few-shot Prompting or Supervised Tuning? A Comparative Study of {LLM}s for Linguistically Distant Language Pairs in {BDI}",
author = "Naorem, Deepen and
Singh, Sanasam Ranbir and
Singh, Telem Joyson and
Sarmah, Priyankoo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.943/",
doi = "10.63317/5aqjysq8avd3",
pages = "12042--12053",
abstract = "Bilingual Dictionary Induction (BDI) presents significant challenges in distant language pairs, particularly in light of the non-isomorphic nature and complexity of linguistic structures. This paper systematically evaluates the performance of unsupervised, supervised fine-tuning, and few-shot prompting approaches on BDI using Large Language Models (LLMs) on a diverse set of distant language pairs. The unsupervised approach explores the inherent multilingual capabilities of LLMs without fine-tuning, while the supervised fine-tuning method utilizes extensive labeled datasets to train models explicitly for BDI tasks. On the other hand, few-shot prompting leverages minimal examples to elicit accurate responses from the LLMs in a zero-shot or few-shot learning paradigm. Our experimental results reveal that the 5-shot prompting approach outperforms unsupervised and zero-shot settings in all cases and surpasses supervised settings in 82.86{\%} of the cases. Few-shot prompting demonstrates robustness against overfitting, leveraging LLMs' in-context learning and multilingual capabilities, making it particularly effective in target-to-source translation, even for morphologically complex language pairs. At the same time, few-shot prompting in LLM models, such as Llama, remains ineffective for morphologically rich language pairs like En-Mn and En-Ta in source-to-target BDI tasks. These findings suggest that few-shot prompting is a cost-effective and powerful alternative for BDI tasks, with future work enhancing BDI tasks in morphologically rich pairs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naorem-etal-2026-shot">
<titleInfo>
<title>Few-shot Prompting or Supervised Tuning? A Comparative Study of LLMs for Linguistically Distant Language Pairs in BDI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepen</namePart>
<namePart type="family">Naorem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanasam</namePart>
<namePart type="given">Ranbir</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Priyankoo</namePart>
<namePart type="family">Sarmah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bilingual Dictionary Induction (BDI) presents significant challenges in distant language pairs, particularly in light of the non-isomorphic nature and complexity of linguistic structures. This paper systematically evaluates the performance of unsupervised, supervised fine-tuning, and few-shot prompting approaches on BDI using Large Language Models (LLMs) on a diverse set of distant language pairs. The unsupervised approach explores the inherent multilingual capabilities of LLMs without fine-tuning, while the supervised fine-tuning method utilizes extensive labeled datasets to train models explicitly for BDI tasks. On the other hand, few-shot prompting leverages minimal examples to elicit accurate responses from the LLMs in a zero-shot or few-shot learning paradigm. Our experimental results reveal that the 5-shot prompting approach outperforms unsupervised and zero-shot settings in all cases and surpasses supervised settings in 82.86% of the cases. Few-shot prompting demonstrates robustness against overfitting, leveraging LLMs’ in-context learning and multilingual capabilities, making it particularly effective in target-to-source translation, even for morphologically complex language pairs. At the same time, few-shot prompting in LLM models, such as Llama, remains ineffective for morphologically rich language pairs like En-Mn and En-Ta in source-to-target BDI tasks. These findings suggest that few-shot prompting is a cost-effective and powerful alternative for BDI tasks, with future work enhancing BDI tasks in morphologically rich pairs.</abstract>
<identifier type="citekey">naorem-etal-2026-shot</identifier>
<identifier type="doi">10.63317/5aqjysq8avd3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.943/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>12042</start>
<end>12053</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-shot Prompting or Supervised Tuning? A Comparative Study of LLMs for Linguistically Distant Language Pairs in BDI
%A Naorem, Deepen
%A Singh, Sanasam Ranbir
%A Singh, Telem Joyson
%A Sarmah, Priyankoo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F naorem-etal-2026-shot
%X Bilingual Dictionary Induction (BDI) presents significant challenges in distant language pairs, particularly in light of the non-isomorphic nature and complexity of linguistic structures. This paper systematically evaluates the performance of unsupervised, supervised fine-tuning, and few-shot prompting approaches on BDI using Large Language Models (LLMs) on a diverse set of distant language pairs. The unsupervised approach explores the inherent multilingual capabilities of LLMs without fine-tuning, while the supervised fine-tuning method utilizes extensive labeled datasets to train models explicitly for BDI tasks. On the other hand, few-shot prompting leverages minimal examples to elicit accurate responses from the LLMs in a zero-shot or few-shot learning paradigm. Our experimental results reveal that the 5-shot prompting approach outperforms unsupervised and zero-shot settings in all cases and surpasses supervised settings in 82.86% of the cases. Few-shot prompting demonstrates robustness against overfitting, leveraging LLMs’ in-context learning and multilingual capabilities, making it particularly effective in target-to-source translation, even for morphologically complex language pairs. At the same time, few-shot prompting in LLM models, such as Llama, remains ineffective for morphologically rich language pairs like En-Mn and En-Ta in source-to-target BDI tasks. These findings suggest that few-shot prompting is a cost-effective and powerful alternative for BDI tasks, with future work enhancing BDI tasks in morphologically rich pairs.
%R 10.63317/5aqjysq8avd3
%U https://aclanthology.org/2026.lrec-1.943/
%U https://doi.org/10.63317/5aqjysq8avd3
%P 12042-12053
Markdown (Informal)
[Few-shot Prompting or Supervised Tuning? A Comparative Study of LLMs for Linguistically Distant Language Pairs in BDI](https://aclanthology.org/2026.lrec-1.943/) (Naorem et al., LREC 2026)
ACL