@inproceedings{maharaj-etal-2024-evaluation,
title = "Evaluation and Continual Improvement for an Enterprise {AI} Assistant",
author = "Maharaj, Akash and
Qian, Kun and
Bhattacharya, Uttaran and
Fang, Sally and
Galatanu, Horia and
Garg, Manas and
Hanessian, Rachel and
Kapoor, Nishant and
Russell, Ken and
Vaithyanathan, Shivakumar and
Li, Yunyao",
editor = "Dragut, Eduard and
Li, Yunyao and
Popa, Lucian and
Vucetic, Slobodan and
Srivastava, Shashank",
booktitle = "Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.dash-1.3",
doi = "10.18653/v1/2024.dash-1.3",
pages = "17--24",
abstract = "The development of conversational AI assistants is an iterative process with many components involved. As such, the evaluation and continual improvement of these assistants is a complex and multifaceted problem. This paper introduces the challenges in evaluating and improving a generative AI assistant for enterprise that is under active development and how we address these challenges. We also share preliminary results and discuss lessons learned.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maharaj-etal-2024-evaluation">
<titleInfo>
<title>Evaluation and Continual Improvement for an Enterprise AI Assistant</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Maharaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uttaran</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sally</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horia</namePart>
<namePart type="family">Galatanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manas</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Hanessian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nishant</namePart>
<namePart type="family">Kapoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ken</namePart>
<namePart type="family">Russell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivakumar</namePart>
<namePart type="family">Vaithyanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Dragut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucian</namePart>
<namePart type="family">Popa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slobodan</namePart>
<namePart type="family">Vucetic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of conversational AI assistants is an iterative process with many components involved. As such, the evaluation and continual improvement of these assistants is a complex and multifaceted problem. This paper introduces the challenges in evaluating and improving a generative AI assistant for enterprise that is under active development and how we address these challenges. We also share preliminary results and discuss lessons learned.</abstract>
<identifier type="citekey">maharaj-etal-2024-evaluation</identifier>
<identifier type="doi">10.18653/v1/2024.dash-1.3</identifier>
<location>
<url>https://aclanthology.org/2024.dash-1.3</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>17</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation and Continual Improvement for an Enterprise AI Assistant
%A Maharaj, Akash
%A Qian, Kun
%A Bhattacharya, Uttaran
%A Fang, Sally
%A Galatanu, Horia
%A Garg, Manas
%A Hanessian, Rachel
%A Kapoor, Nishant
%A Russell, Ken
%A Vaithyanathan, Shivakumar
%A Li, Yunyao
%Y Dragut, Eduard
%Y Li, Yunyao
%Y Popa, Lucian
%Y Vucetic, Slobodan
%Y Srivastava, Shashank
%S Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F maharaj-etal-2024-evaluation
%X The development of conversational AI assistants is an iterative process with many components involved. As such, the evaluation and continual improvement of these assistants is a complex and multifaceted problem. This paper introduces the challenges in evaluating and improving a generative AI assistant for enterprise that is under active development and how we address these challenges. We also share preliminary results and discuss lessons learned.
%R 10.18653/v1/2024.dash-1.3
%U https://aclanthology.org/2024.dash-1.3
%U https://doi.org/10.18653/v1/2024.dash-1.3
%P 17-24
Markdown (Informal)
[Evaluation and Continual Improvement for an Enterprise AI Assistant](https://aclanthology.org/2024.dash-1.3) (Maharaj et al., DaSH-WS 2024)
ACL
- Akash Maharaj, Kun Qian, Uttaran Bhattacharya, Sally Fang, Horia Galatanu, Manas Garg, Rachel Hanessian, Nishant Kapoor, Ken Russell, Shivakumar Vaithyanathan, and Yunyao Li. 2024. Evaluation and Continual Improvement for an Enterprise AI Assistant. In Proceedings of the Fifth Workshop on Data Science with Human-in-the-Loop (DaSH 2024), pages 17–24, Mexico City, Mexico. Association for Computational Linguistics.