@inproceedings{laskar-etal-2024-query,
title = "Query-{OPT}: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization",
author = "Laskar, Md Tahmid Rahman and
Khasanova, Elena and
Fu, Xue-Yong and
Chen, Cheng and
Tn, Shashi Bhushan",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.86",
pages = "1140--1151",
abstract = "This work focuses on the task of query-based meeting summarization in which the summary of a context (meeting transcript) is generated in response to a specific query. When using Large Language Models (LLMs) for this task, a new call to the LLM inference endpoint/API is required for each new query even if the context stays the same. However, repeated calls to the LLM inference endpoints would significantly increase the costs of using them in production, making LLMs impractical for many real-world use cases. To address this problem, in this paper, we investigate whether combining the queries for the same input context in a single prompt to minimize repeated calls can be successfully used in meeting summarization. In this regard, we conduct extensive experiments by comparing the performance of various popular LLMs: GPT-4, Gemini, Claude-3, LLaMA2, Mistral, Phi-3, and Qwen-2 in single-query and multi-query settings. We observe that the capability to reliably generate the response in the expected format is usually limited to closedsource LLMs, with most open-source LLMs lagging behind (except Mistral). We conclude that multi-query prompting could be useful to optimize the inference costs by significantly reducing calls to the inference endpoints/APIs for the task of meeting summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laskar-etal-2024-query">
<titleInfo>
<title>Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Khasanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="given">Bhushan</namePart>
<namePart type="family">Tn</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work focuses on the task of query-based meeting summarization in which the summary of a context (meeting transcript) is generated in response to a specific query. When using Large Language Models (LLMs) for this task, a new call to the LLM inference endpoint/API is required for each new query even if the context stays the same. However, repeated calls to the LLM inference endpoints would significantly increase the costs of using them in production, making LLMs impractical for many real-world use cases. To address this problem, in this paper, we investigate whether combining the queries for the same input context in a single prompt to minimize repeated calls can be successfully used in meeting summarization. In this regard, we conduct extensive experiments by comparing the performance of various popular LLMs: GPT-4, Gemini, Claude-3, LLaMA2, Mistral, Phi-3, and Qwen-2 in single-query and multi-query settings. We observe that the capability to reliably generate the response in the expected format is usually limited to closedsource LLMs, with most open-source LLMs lagging behind (except Mistral). We conclude that multi-query prompting could be useful to optimize the inference costs by significantly reducing calls to the inference endpoints/APIs for the task of meeting summarization.</abstract>
<identifier type="citekey">laskar-etal-2024-query</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.86</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1140</start>
<end>1151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization
%A Laskar, Md Tahmid Rahman
%A Khasanova, Elena
%A Fu, Xue-Yong
%A Chen, Cheng
%A Tn, Shashi Bhushan
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F laskar-etal-2024-query
%X This work focuses on the task of query-based meeting summarization in which the summary of a context (meeting transcript) is generated in response to a specific query. When using Large Language Models (LLMs) for this task, a new call to the LLM inference endpoint/API is required for each new query even if the context stays the same. However, repeated calls to the LLM inference endpoints would significantly increase the costs of using them in production, making LLMs impractical for many real-world use cases. To address this problem, in this paper, we investigate whether combining the queries for the same input context in a single prompt to minimize repeated calls can be successfully used in meeting summarization. In this regard, we conduct extensive experiments by comparing the performance of various popular LLMs: GPT-4, Gemini, Claude-3, LLaMA2, Mistral, Phi-3, and Qwen-2 in single-query and multi-query settings. We observe that the capability to reliably generate the response in the expected format is usually limited to closedsource LLMs, with most open-source LLMs lagging behind (except Mistral). We conclude that multi-query prompting could be useful to optimize the inference costs by significantly reducing calls to the inference endpoints/APIs for the task of meeting summarization.
%U https://aclanthology.org/2024.emnlp-industry.86
%P 1140-1151
Markdown (Informal)
[Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization](https://aclanthology.org/2024.emnlp-industry.86) (Laskar et al., EMNLP 2024)
ACL