@article{zhang-etal-2024-benchmarking,
title = "Benchmarking Large Language Models for News Summarization",
author = "Zhang, Tianyi and
Ladhak, Faisal and
Durmus, Esin and
Liang, Percy and
McKeown, Kathleen and
Hashimoto, Tatsunori B.",
journal = "Transactions of the Association for Computational Linguistics",
volume = "12",
year = "2024",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2024.tacl-1.3",
doi = "10.1162/tacl_a_00632",
pages = "39--57",
abstract = "Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model scales, we make two important observations. First, we find instruction tuning, not model size, is the key to the LLM{'}s zero-shot summarization capability. Second, existing studies have been limited by low-quality references, leading to underestimates of human performance and lower few-shot and finetuning performance. To better evaluate LLMs, we perform human evaluation over high-quality summaries we collect from freelance writers. Despite major stylistic differences such as the amount of paraphrasing, we find that LLM summaries are judged to be on par with human written summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-benchmarking">
<titleInfo>
<title>Benchmarking Large Language Models for News Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="family">Ladhak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Percy</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsunori</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model scales, we make two important observations. First, we find instruction tuning, not model size, is the key to the LLM’s zero-shot summarization capability. Second, existing studies have been limited by low-quality references, leading to underestimates of human performance and lower few-shot and finetuning performance. To better evaluate LLMs, we perform human evaluation over high-quality summaries we collect from freelance writers. Despite major stylistic differences such as the amount of paraphrasing, we find that LLM summaries are judged to be on par with human written summaries.</abstract>
<identifier type="citekey">zhang-etal-2024-benchmarking</identifier>
<identifier type="doi">10.1162/tacl_a_00632</identifier>
<location>
<url>https://aclanthology.org/2024.tacl-1.3</url>
</location>
<part>
<date>2024</date>
<detail type="volume"><number>12</number></detail>
<extent unit="page">
<start>39</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Benchmarking Large Language Models for News Summarization
%A Zhang, Tianyi
%A Ladhak, Faisal
%A Durmus, Esin
%A Liang, Percy
%A McKeown, Kathleen
%A Hashimoto, Tatsunori B.
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F zhang-etal-2024-benchmarking
%X Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model scales, we make two important observations. First, we find instruction tuning, not model size, is the key to the LLM’s zero-shot summarization capability. Second, existing studies have been limited by low-quality references, leading to underestimates of human performance and lower few-shot and finetuning performance. To better evaluate LLMs, we perform human evaluation over high-quality summaries we collect from freelance writers. Despite major stylistic differences such as the amount of paraphrasing, we find that LLM summaries are judged to be on par with human written summaries.
%R 10.1162/tacl_a_00632
%U https://aclanthology.org/2024.tacl-1.3
%U https://doi.org/10.1162/tacl_a_00632
%P 39-57
Markdown (Informal)
[Benchmarking Large Language Models for News Summarization](https://aclanthology.org/2024.tacl-1.3) (Zhang et al., TACL 2024)
ACL