@inproceedings{platek-etal-2023-three,
title = "Three Ways of Using Large Language Models to Evaluate Chat",
author = "Pl{\'a}tek, Ond{\v{r}}ej and
Hudecek, Vojtech and
Schmidtova, Patricia and
Lango, Mateusz and
Dusek, Ondrej",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.14",
pages = "113--122",
abstract = "This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition. We present three different approaches to predicting turn-level qualities of chatbot responses based on large language models (LLMs). We report improvement over the baseline using dynamic few-shot examples from a vector store for the prompts for ChatGPT. We also analyze the performance of the other two approaches and report needed improvements for future work. We developed the three systems over just two weeks, showing the potential of LLMs for this task. An ablation study conducted after the challenge deadline shows that the new Llama 2 models are closing the performance gap between ChatGPT and open-source LLMs. However, we find that the Llama 2 models do not benefit from few-shot examples in the same way as ChatGPT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="platek-etal-2023-three">
<titleInfo>
<title>Three Ways of Using Large Language Models to Evaluate Chat</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Plátek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vojtech</namePart>
<namePart type="family">Hudecek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Schmidtova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Lango</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition. We present three different approaches to predicting turn-level qualities of chatbot responses based on large language models (LLMs). We report improvement over the baseline using dynamic few-shot examples from a vector store for the prompts for ChatGPT. We also analyze the performance of the other two approaches and report needed improvements for future work. We developed the three systems over just two weeks, showing the potential of LLMs for this task. An ablation study conducted after the challenge deadline shows that the new Llama 2 models are closing the performance gap between ChatGPT and open-source LLMs. However, we find that the Llama 2 models do not benefit from few-shot examples in the same way as ChatGPT.</abstract>
<identifier type="citekey">platek-etal-2023-three</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.14</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>113</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Three Ways of Using Large Language Models to Evaluate Chat
%A Plátek, Ondřej
%A Hudecek, Vojtech
%A Schmidtova, Patricia
%A Lango, Mateusz
%A Dusek, Ondrej
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F platek-etal-2023-three
%X This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition. We present three different approaches to predicting turn-level qualities of chatbot responses based on large language models (LLMs). We report improvement over the baseline using dynamic few-shot examples from a vector store for the prompts for ChatGPT. We also analyze the performance of the other two approaches and report needed improvements for future work. We developed the three systems over just two weeks, showing the potential of LLMs for this task. An ablation study conducted after the challenge deadline shows that the new Llama 2 models are closing the performance gap between ChatGPT and open-source LLMs. However, we find that the Llama 2 models do not benefit from few-shot examples in the same way as ChatGPT.
%U https://aclanthology.org/2023.dstc-1.14
%P 113-122
Markdown (Informal)
[Three Ways of Using Large Language Models to Evaluate Chat](https://aclanthology.org/2023.dstc-1.14) (Plátek et al., DSTC-WS 2023)
ACL
- Ondřej Plátek, Vojtech Hudecek, Patricia Schmidtova, Mateusz Lango, and Ondrej Dusek. 2023. Three Ways of Using Large Language Models to Evaluate Chat. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 113–122, Prague, Czech Republic. Association for Computational Linguistics.