@inproceedings{sicilia-etal-2024-humbel,
title = "{H}um{BEL}: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations",
author = "Sicilia, Anthony and
Gates, Jennifer and
Alikhani, Malihe",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.68",
pages = "1127--1143",
abstract = "While demographic factors like age and gender change the way people talk, and in particular, the way people talk to machines, there is little investigation into how large pre-trained language models (LMs) can adapt to these changes. To remedy this gap, we consider how demographic factors in LM language skills can be measured to determine compatibility with a target demographic. We suggest clinical techniques from Speech Language Pathology, which has norms for acquisition of language skills in humans. We conduct evaluation with a domain expert (i.e., a clinically licensed speech language pathologist), and also propose automated techniques to complement clinical evaluation at scale. Empirically, we focus on age, finding LM capability varies widely depending on task: GPT-3.5 mimics the ability of humans ranging from age 6-15 at tasks requiring inference, and simultaneously, outperforms a typical 21 year old at memorization. GPT-3.5 also has trouble with social language use, exhibiting less than 50{\%} of the tested pragmatic skills. Findings affirm the importance of considering demographic alignment and conversational goals when using LMs as public-facing tools. Code, data, and a package will be available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sicilia-etal-2024-humbel">
<titleInfo>
<title>HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Sicilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Gates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While demographic factors like age and gender change the way people talk, and in particular, the way people talk to machines, there is little investigation into how large pre-trained language models (LMs) can adapt to these changes. To remedy this gap, we consider how demographic factors in LM language skills can be measured to determine compatibility with a target demographic. We suggest clinical techniques from Speech Language Pathology, which has norms for acquisition of language skills in humans. We conduct evaluation with a domain expert (i.e., a clinically licensed speech language pathologist), and also propose automated techniques to complement clinical evaluation at scale. Empirically, we focus on age, finding LM capability varies widely depending on task: GPT-3.5 mimics the ability of humans ranging from age 6-15 at tasks requiring inference, and simultaneously, outperforms a typical 21 year old at memorization. GPT-3.5 also has trouble with social language use, exhibiting less than 50% of the tested pragmatic skills. Findings affirm the importance of considering demographic alignment and conversational goals when using LMs as public-facing tools. Code, data, and a package will be available.</abstract>
<identifier type="citekey">sicilia-etal-2024-humbel</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.68</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1127</start>
<end>1143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations
%A Sicilia, Anthony
%A Gates, Jennifer
%A Alikhani, Malihe
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F sicilia-etal-2024-humbel
%X While demographic factors like age and gender change the way people talk, and in particular, the way people talk to machines, there is little investigation into how large pre-trained language models (LMs) can adapt to these changes. To remedy this gap, we consider how demographic factors in LM language skills can be measured to determine compatibility with a target demographic. We suggest clinical techniques from Speech Language Pathology, which has norms for acquisition of language skills in humans. We conduct evaluation with a domain expert (i.e., a clinically licensed speech language pathologist), and also propose automated techniques to complement clinical evaluation at scale. Empirically, we focus on age, finding LM capability varies widely depending on task: GPT-3.5 mimics the ability of humans ranging from age 6-15 at tasks requiring inference, and simultaneously, outperforms a typical 21 year old at memorization. GPT-3.5 also has trouble with social language use, exhibiting less than 50% of the tested pragmatic skills. Findings affirm the importance of considering demographic alignment and conversational goals when using LMs as public-facing tools. Code, data, and a package will be available.
%U https://aclanthology.org/2024.eacl-long.68
%P 1127-1143
Markdown (Informal)
[HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations](https://aclanthology.org/2024.eacl-long.68) (Sicilia et al., EACL 2024)
ACL