@inproceedings{balloccu-etal-2024-ask,
title = "Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-{AI} collaboration",
author = "Balloccu, Simone and
Reiter, Ehud and
Li, Karen and
Sargsyan, Rafael and
Kumar, Vivek and
Reforgiato, Diego and
Riboni, Daniele and
Dusek, Ondrej",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.674",
pages = "11519--11545",
abstract = "Large Language Models (LLMs) are being employed by end-users for various tasks, including sensitive ones such as health counseling, disregarding potential safety concerns. It is thus necessary to understand how adequately LLMs perform in such domains. We conduct a case study on ChatGPT in nutrition counseling, a popular use-case where the model supports a user with their dietary struggles. We crowd-source real-world diet-related struggles, then work with nutrition experts to generate supportive text using ChatGPT. Finally, experts evaluate the safety and text quality of ChatGPT{'}s output. The result is the HAI-coaching dataset, containing {\textasciitilde}2.4K crowdsourced dietary struggles and {\textasciitilde}97K corresponding ChatGPT-generated and expert-annotated supportive texts. We analyse ChatGPT{'}s performance, discovering potentially harmful behaviours, especially for sensitive topics like mental health. Finally, we use HAI-coaching to test open LLMs on various downstream tasks, showing that even the latest models struggle to achieve good performance. HAI-coaching is available at https://github.com/uccollab/hai-coaching/",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balloccu-etal-2024-ask">
<titleInfo>
<title>Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Sargsyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Reforgiato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Riboni</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>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are being employed by end-users for various tasks, including sensitive ones such as health counseling, disregarding potential safety concerns. It is thus necessary to understand how adequately LLMs perform in such domains. We conduct a case study on ChatGPT in nutrition counseling, a popular use-case where the model supports a user with their dietary struggles. We crowd-source real-world diet-related struggles, then work with nutrition experts to generate supportive text using ChatGPT. Finally, experts evaluate the safety and text quality of ChatGPT’s output. The result is the HAI-coaching dataset, containing ~2.4K crowdsourced dietary struggles and ~97K corresponding ChatGPT-generated and expert-annotated supportive texts. We analyse ChatGPT’s performance, discovering potentially harmful behaviours, especially for sensitive topics like mental health. Finally, we use HAI-coaching to test open LLMs on various downstream tasks, showing that even the latest models struggle to achieve good performance. HAI-coaching is available at https://github.com/uccollab/hai-coaching/</abstract>
<identifier type="citekey">balloccu-etal-2024-ask</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.674</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11519</start>
<end>11545</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration
%A Balloccu, Simone
%A Reiter, Ehud
%A Li, Karen
%A Sargsyan, Rafael
%A Kumar, Vivek
%A Reforgiato, Diego
%A Riboni, Daniele
%A Dusek, Ondrej
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F balloccu-etal-2024-ask
%X Large Language Models (LLMs) are being employed by end-users for various tasks, including sensitive ones such as health counseling, disregarding potential safety concerns. It is thus necessary to understand how adequately LLMs perform in such domains. We conduct a case study on ChatGPT in nutrition counseling, a popular use-case where the model supports a user with their dietary struggles. We crowd-source real-world diet-related struggles, then work with nutrition experts to generate supportive text using ChatGPT. Finally, experts evaluate the safety and text quality of ChatGPT’s output. The result is the HAI-coaching dataset, containing ~2.4K crowdsourced dietary struggles and ~97K corresponding ChatGPT-generated and expert-annotated supportive texts. We analyse ChatGPT’s performance, discovering potentially harmful behaviours, especially for sensitive topics like mental health. Finally, we use HAI-coaching to test open LLMs on various downstream tasks, showing that even the latest models struggle to achieve good performance. HAI-coaching is available at https://github.com/uccollab/hai-coaching/
%U https://aclanthology.org/2024.findings-emnlp.674
%P 11519-11545
Markdown (Informal)
[Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration](https://aclanthology.org/2024.findings-emnlp.674) (Balloccu et al., Findings 2024)
ACL
- Simone Balloccu, Ehud Reiter, Karen Li, Rafael Sargsyan, Vivek Kumar, Diego Reforgiato, Daniele Riboni, and Ondrej Dusek. 2024. Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11519–11545, Miami, Florida, USA. Association for Computational Linguistics.