@inproceedings{tahaei-etal-2024-efficient,
title = "Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification",
author = "Tahaei, Marzieh and
Jafari, Aref and
Rashid, Ahmad and
Alfonso-Hermelo, David and
Bibi, Khalil and
Wu, Yimeng and
Ghodsi, Ali and
Chen, Boxing and
Rezagholizadeh, Mehdi",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.277",
doi = "10.18653/v1/2024.findings-naacl.277",
pages = "4443--4450",
abstract = "In recent years, there has been a growing interest in utilizing external knowledge to reduce hallucinations in large language models (LLMs) and provide them with updated information. Despite this improvement, a major challenge lies in the lack of explicit citations, which hampers the ability to verify the information generated by these models.This paper focuses on providing models with citation capabilities efficiently. By constructing a dataset of citations, we train two model architectures: an FID-style FLAN-T5 model for efficient answer composition and a 13B model known for its success in instruction following after tuning. Evaluation on fluency, correctness, and citation quality is conducted through human assessment and the newly introduced Automatic LLMs{'} Citation Evaluation (ALCE) benchmark.Results demonstrate significant improvements in answer quality and efficiency, surpassing the performance of the popular ChatGPT on some of the metrics. The models exhibit exceptional out-of-domain generalization in both human and automatic evaluation. Notably, the FID-style FLAN-T5 model with only 3B parameters performs impressively compared to the 13B model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahaei-etal-2024-efficient">
<titleInfo>
<title>Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Tahaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aref</namePart>
<namePart type="family">Jafari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfonso-Hermelo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Bibi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Ghodsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Rezagholizadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, there has been a growing interest in utilizing external knowledge to reduce hallucinations in large language models (LLMs) and provide them with updated information. Despite this improvement, a major challenge lies in the lack of explicit citations, which hampers the ability to verify the information generated by these models.This paper focuses on providing models with citation capabilities efficiently. By constructing a dataset of citations, we train two model architectures: an FID-style FLAN-T5 model for efficient answer composition and a 13B model known for its success in instruction following after tuning. Evaluation on fluency, correctness, and citation quality is conducted through human assessment and the newly introduced Automatic LLMs’ Citation Evaluation (ALCE) benchmark.Results demonstrate significant improvements in answer quality and efficiency, surpassing the performance of the popular ChatGPT on some of the metrics. The models exhibit exceptional out-of-domain generalization in both human and automatic evaluation. Notably, the FID-style FLAN-T5 model with only 3B parameters performs impressively compared to the 13B model.</abstract>
<identifier type="citekey">tahaei-etal-2024-efficient</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.277</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.277</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4443</start>
<end>4450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
%A Tahaei, Marzieh
%A Jafari, Aref
%A Rashid, Ahmad
%A Alfonso-Hermelo, David
%A Bibi, Khalil
%A Wu, Yimeng
%A Ghodsi, Ali
%A Chen, Boxing
%A Rezagholizadeh, Mehdi
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F tahaei-etal-2024-efficient
%X In recent years, there has been a growing interest in utilizing external knowledge to reduce hallucinations in large language models (LLMs) and provide them with updated information. Despite this improvement, a major challenge lies in the lack of explicit citations, which hampers the ability to verify the information generated by these models.This paper focuses on providing models with citation capabilities efficiently. By constructing a dataset of citations, we train two model architectures: an FID-style FLAN-T5 model for efficient answer composition and a 13B model known for its success in instruction following after tuning. Evaluation on fluency, correctness, and citation quality is conducted through human assessment and the newly introduced Automatic LLMs’ Citation Evaluation (ALCE) benchmark.Results demonstrate significant improvements in answer quality and efficiency, surpassing the performance of the popular ChatGPT on some of the metrics. The models exhibit exceptional out-of-domain generalization in both human and automatic evaluation. Notably, the FID-style FLAN-T5 model with only 3B parameters performs impressively compared to the 13B model.
%R 10.18653/v1/2024.findings-naacl.277
%U https://aclanthology.org/2024.findings-naacl.277
%U https://doi.org/10.18653/v1/2024.findings-naacl.277
%P 4443-4450
Markdown (Informal)
[Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification](https://aclanthology.org/2024.findings-naacl.277) (Tahaei et al., Findings 2024)
ACL
- Marzieh Tahaei, Aref Jafari, Ahmad Rashid, David Alfonso-Hermelo, Khalil Bibi, Yimeng Wu, Ali Ghodsi, Boxing Chen, and Mehdi Rezagholizadeh. 2024. Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4443–4450, Mexico City, Mexico. Association for Computational Linguistics.