@inproceedings{kotonya-etal-2023-little,
title = "Little Giants: Exploring the Potential of Small {LLM}s as Evaluation Metrics in Summarization in the {E}val4{NLP} 2023 Shared Task",
author = "Kotonya, Neema and
Krishnasamy, Saran and
Tetreault, Joel and
Jaimes, Alejandro",
editor = {Deutsch, Daniel and
Dror, Rotem and
Eger, Steffen and
Gao, Yang and
Leiter, Christoph and
Opitz, Juri and
R{\"u}ckl{\'e}, Andreas},
booktitle = "Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eval4nlp-1.17/",
doi = "10.18653/v1/2023.eval4nlp-1.17",
pages = "202--218",
abstract = "This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries. We conducted systematic experiments with various prompting techniques, including standard prompting, prompts informed by annotator instructions, and innovative chain-of-thought prompting. In addition, we integrated these approaches with zero-shot and one-shot learning methods to maximize the efficacy of our evaluation procedures. Our work reveals that combining these approaches using a {\textquotedblleft}small{\textquotedblright}, open source model (orca{\_}mini{\_}v3{\_}7B) yields competitive results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kotonya-etal-2023-little">
<titleInfo>
<title>Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saran</namePart>
<namePart type="family">Krishnasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Jaimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Deutsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Leiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Rücklé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bali, Indonesia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries. We conducted systematic experiments with various prompting techniques, including standard prompting, prompts informed by annotator instructions, and innovative chain-of-thought prompting. In addition, we integrated these approaches with zero-shot and one-shot learning methods to maximize the efficacy of our evaluation procedures. Our work reveals that combining these approaches using a “small”, open source model (orca_mini_v3_7B) yields competitive results.</abstract>
<identifier type="citekey">kotonya-etal-2023-little</identifier>
<identifier type="doi">10.18653/v1/2023.eval4nlp-1.17</identifier>
<location>
<url>https://aclanthology.org/2023.eval4nlp-1.17/</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>202</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task
%A Kotonya, Neema
%A Krishnasamy, Saran
%A Tetreault, Joel
%A Jaimes, Alejandro
%Y Deutsch, Daniel
%Y Dror, Rotem
%Y Eger, Steffen
%Y Gao, Yang
%Y Leiter, Christoph
%Y Opitz, Juri
%Y Rücklé, Andreas
%S Proceedings of the 4th Workshop on Evaluation and Comparison of NLP Systems
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F kotonya-etal-2023-little
%X This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries. We conducted systematic experiments with various prompting techniques, including standard prompting, prompts informed by annotator instructions, and innovative chain-of-thought prompting. In addition, we integrated these approaches with zero-shot and one-shot learning methods to maximize the efficacy of our evaluation procedures. Our work reveals that combining these approaches using a “small”, open source model (orca_mini_v3_7B) yields competitive results.
%R 10.18653/v1/2023.eval4nlp-1.17
%U https://aclanthology.org/2023.eval4nlp-1.17/
%U https://doi.org/10.18653/v1/2023.eval4nlp-1.17
%P 202-218
Markdown (Informal)
[Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task](https://aclanthology.org/2023.eval4nlp-1.17/) (Kotonya et al., Eval4NLP 2023)
ACL