@inproceedings{azime-etal-2024-walia,
title = "Walia-{LLM}: Enhancing {A}mharic-{LL}a{MA} by Integrating Task-Specific and Generative Datasets",
author = "Azime, Israel Abebe and
Tonja, Atnafu Lambebo and
Belay, Tadesse Destaw and
Fuge, Mitiku Yohannes and
Wassie, Aman Kassahun and
Jada, Eyasu Shiferaw and
Chanie, Yonas and
Sewunetie, Walelign Tewabe and
Yimam, Seid Muhie",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.25/",
doi = "10.18653/v1/2024.findings-emnlp.25",
pages = "432--444",
abstract = "Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource languages are left behind due to the unavailability of resources. In this work, we focus on enhancing the LLaMA-2-Amharic model by integrating task-specific and generative datasets to improve language model performance for Amharic. We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model. The fine-tuned model shows promising results in different NLP tasks. We also explore the effectiveness of translated instruction datasets compared to the dataset we created. Our dataset creation pipeline, along with instruction datasets, trained models, and evaluation outputs, is made publicly available to encourage research in language-specific models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azime-etal-2024-walia">
<titleInfo>
<title>Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Israel</namePart>
<namePart type="given">Abebe</namePart>
<namePart type="family">Azime</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="given">Destaw</namePart>
<namePart type="family">Belay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitiku</namePart>
<namePart type="given">Yohannes</namePart>
<namePart type="family">Fuge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="given">Kassahun</namePart>
<namePart type="family">Wassie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eyasu</namePart>
<namePart type="given">Shiferaw</namePart>
<namePart type="family">Jada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonas</namePart>
<namePart type="family">Chanie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walelign</namePart>
<namePart type="given">Tewabe</namePart>
<namePart type="family">Sewunetie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seid</namePart>
<namePart type="given">Muhie</namePart>
<namePart type="family">Yimam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource languages are left behind due to the unavailability of resources. In this work, we focus on enhancing the LLaMA-2-Amharic model by integrating task-specific and generative datasets to improve language model performance for Amharic. We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model. The fine-tuned model shows promising results in different NLP tasks. We also explore the effectiveness of translated instruction datasets compared to the dataset we created. Our dataset creation pipeline, along with instruction datasets, trained models, and evaluation outputs, is made publicly available to encourage research in language-specific models.</abstract>
<identifier type="citekey">azime-etal-2024-walia</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.25</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.25/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>432</start>
<end>444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets
%A Azime, Israel Abebe
%A Tonja, Atnafu Lambebo
%A Belay, Tadesse Destaw
%A Fuge, Mitiku Yohannes
%A Wassie, Aman Kassahun
%A Jada, Eyasu Shiferaw
%A Chanie, Yonas
%A Sewunetie, Walelign Tewabe
%A Yimam, Seid Muhie
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F azime-etal-2024-walia
%X Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource languages are left behind due to the unavailability of resources. In this work, we focus on enhancing the LLaMA-2-Amharic model by integrating task-specific and generative datasets to improve language model performance for Amharic. We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model. The fine-tuned model shows promising results in different NLP tasks. We also explore the effectiveness of translated instruction datasets compared to the dataset we created. Our dataset creation pipeline, along with instruction datasets, trained models, and evaluation outputs, is made publicly available to encourage research in language-specific models.
%R 10.18653/v1/2024.findings-emnlp.25
%U https://aclanthology.org/2024.findings-emnlp.25/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.25
%P 432-444
Markdown (Informal)
[Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets](https://aclanthology.org/2024.findings-emnlp.25/) (Azime et al., Findings 2024)
ACL
- Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay, Mitiku Yohannes Fuge, Aman Kassahun Wassie, Eyasu Shiferaw Jada, Yonas Chanie, Walelign Tewabe Sewunetie, and Seid Muhie Yimam. 2024. Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 432–444, Miami, Florida, USA. Association for Computational Linguistics.