@inproceedings{hung-etal-2023-walking,
title = "Walking a Tightrope {--} Evaluating Large Language Models in High-Risk Domains",
author = "Hung, Chia-Chien and
Ben Rim, Wiem and
Frost, Lindsay and
Bruckner, Lars and
Lawrence, Carolin",
editor = "Hupkes, Dieuwke and
Dankers, Verna and
Batsuren, Khuyagbaatar and
Sinha, Koustuv and
Kazemnejad, Amirhossein and
Christodoulopoulos, Christos and
Cotterell, Ryan and
Bruni, Elia",
booktitle = "Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.genbench-1.8",
doi = "10.18653/v1/2023.genbench-1.8",
pages = "99--111",
abstract = "High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Further qualitative analysis highlights the existing limitations inherent in current LLMs when evaluating in high-risk domains. This underscores the essential nature of not only improving LLM capabilities but also prioritizing the refinement of domain-specific metrics, and embracing a more human-centric approach to enhance safety and factual reliability. Our findings advance the field toward the concerns of properly evaluating LLMs in high-risk domains, aiming to steer the adaptability of LLMs in fulfilling societal obligations and aligning with forthcoming regulations, such as the EU AI Act.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hung-etal-2023-walking">
<titleInfo>
<title>Walking a Tightrope – Evaluating Large Language Models in High-Risk Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chia-Chien</namePart>
<namePart type="family">Hung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiem</namePart>
<namePart type="family">Ben Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lindsay</namePart>
<namePart type="family">Frost</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Bruckner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolin</namePart>
<namePart type="family">Lawrence</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>Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verna</namePart>
<namePart type="family">Dankers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khuyagbaatar</namePart>
<namePart type="family">Batsuren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustuv</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Kazemnejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</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>High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Further qualitative analysis highlights the existing limitations inherent in current LLMs when evaluating in high-risk domains. This underscores the essential nature of not only improving LLM capabilities but also prioritizing the refinement of domain-specific metrics, and embracing a more human-centric approach to enhance safety and factual reliability. Our findings advance the field toward the concerns of properly evaluating LLMs in high-risk domains, aiming to steer the adaptability of LLMs in fulfilling societal obligations and aligning with forthcoming regulations, such as the EU AI Act.</abstract>
<identifier type="citekey">hung-etal-2023-walking</identifier>
<identifier type="doi">10.18653/v1/2023.genbench-1.8</identifier>
<location>
<url>https://aclanthology.org/2023.genbench-1.8</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>99</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Walking a Tightrope – Evaluating Large Language Models in High-Risk Domains
%A Hung, Chia-Chien
%A Ben Rim, Wiem
%A Frost, Lindsay
%A Bruckner, Lars
%A Lawrence, Carolin
%Y Hupkes, Dieuwke
%Y Dankers, Verna
%Y Batsuren, Khuyagbaatar
%Y Sinha, Koustuv
%Y Kazemnejad, Amirhossein
%Y Christodoulopoulos, Christos
%Y Cotterell, Ryan
%Y Bruni, Elia
%S Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F hung-etal-2023-walking
%X High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Further qualitative analysis highlights the existing limitations inherent in current LLMs when evaluating in high-risk domains. This underscores the essential nature of not only improving LLM capabilities but also prioritizing the refinement of domain-specific metrics, and embracing a more human-centric approach to enhance safety and factual reliability. Our findings advance the field toward the concerns of properly evaluating LLMs in high-risk domains, aiming to steer the adaptability of LLMs in fulfilling societal obligations and aligning with forthcoming regulations, such as the EU AI Act.
%R 10.18653/v1/2023.genbench-1.8
%U https://aclanthology.org/2023.genbench-1.8
%U https://doi.org/10.18653/v1/2023.genbench-1.8
%P 99-111
Markdown (Informal)
[Walking a Tightrope – Evaluating Large Language Models in High-Risk Domains](https://aclanthology.org/2023.genbench-1.8) (Hung et al., GenBench-WS 2023)
ACL