@inproceedings{santra-etal-2023-frugal,
title = "Frugal Prompting for Dialog Models",
author = "Santra, Bishal and
Basak, Sakya and
De, Abhinandan and
Gupta, Manish and
Goyal, Pawan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.290",
doi = "10.18653/v1/2023.findings-emnlp.290",
pages = "4383--4407",
abstract = "The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models{'} abilities, a better understanding of their behavior for different input protocols is required. With LLMs, users can directly interact with the models through a text-based interface to define and solve various tasks. Hence, understanding the conversational abilities of these LLMs, which may not have been specifically trained for dialog modeling, is also important. This study examines different approaches for building dialog systems using LLMs by considering various aspects of the prompt. As part of prompt tuning, we experiment with various ways of providing instructions, exemplars, current query and additional context. The research also analyzes the representations of dialog history that have the optimal usable-information density. Based on the findings, the paper suggests more compact ways of providing dialog history information while ensuring good performance and reducing model{'}s inference-API costs. The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santra-etal-2023-frugal">
<titleInfo>
<title>Frugal Prompting for Dialog Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bishal</namePart>
<namePart type="family">Santra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakya</namePart>
<namePart type="family">Basak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinandan</namePart>
<namePart type="family">De</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models’ abilities, a better understanding of their behavior for different input protocols is required. With LLMs, users can directly interact with the models through a text-based interface to define and solve various tasks. Hence, understanding the conversational abilities of these LLMs, which may not have been specifically trained for dialog modeling, is also important. This study examines different approaches for building dialog systems using LLMs by considering various aspects of the prompt. As part of prompt tuning, we experiment with various ways of providing instructions, exemplars, current query and additional context. The research also analyzes the representations of dialog history that have the optimal usable-information density. Based on the findings, the paper suggests more compact ways of providing dialog history information while ensuring good performance and reducing model’s inference-API costs. The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.</abstract>
<identifier type="citekey">santra-etal-2023-frugal</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.290</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.290</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>4383</start>
<end>4407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Frugal Prompting for Dialog Models
%A Santra, Bishal
%A Basak, Sakya
%A De, Abhinandan
%A Gupta, Manish
%A Goyal, Pawan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F santra-etal-2023-frugal
%X The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models’ abilities, a better understanding of their behavior for different input protocols is required. With LLMs, users can directly interact with the models through a text-based interface to define and solve various tasks. Hence, understanding the conversational abilities of these LLMs, which may not have been specifically trained for dialog modeling, is also important. This study examines different approaches for building dialog systems using LLMs by considering various aspects of the prompt. As part of prompt tuning, we experiment with various ways of providing instructions, exemplars, current query and additional context. The research also analyzes the representations of dialog history that have the optimal usable-information density. Based on the findings, the paper suggests more compact ways of providing dialog history information while ensuring good performance and reducing model’s inference-API costs. The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.
%R 10.18653/v1/2023.findings-emnlp.290
%U https://aclanthology.org/2023.findings-emnlp.290
%U https://doi.org/10.18653/v1/2023.findings-emnlp.290
%P 4383-4407
Markdown (Informal)
[Frugal Prompting for Dialog Models](https://aclanthology.org/2023.findings-emnlp.290) (Santra et al., Findings 2023)
ACL
- Bishal Santra, Sakya Basak, Abhinandan De, Manish Gupta, and Pawan Goyal. 2023. Frugal Prompting for Dialog Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4383–4407, Singapore. Association for Computational Linguistics.