@inproceedings{sandoval-etal-2025-llm,
title = "My {LLM} might Mimic {AAE} - But When Should It?",
author = "Sandoval, Sandra Camille and
Acquaye, Christabel and
Cobbina, Kwesi Adu and
Teli, Mohammad Nayeem and
Iii, Hal Daum{\'e}",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.273/",
doi = "10.18653/v1/2025.naacl-long.273",
pages = "5277--5302",
ISBN = "979-8-89176-189-6",
abstract = "We examine the representation of African American English (AAE) in large language models (LLMs), exploring (a) the perceptions Black Americans have of how effective these technologies are at producing authentic AAE, and (b) in what contexts Black Americans find this desirable. Through both a survey of Black Americans ($n=$ 104) and annotation of LLM-produced AAE by Black Americans ($n=$ 228), we find that Black Americans favor choice and autonomy in determining when AAE is appropriate in LLM output. They tend to prefer that LLMs default to communicating in Mainstream U.S. English in formal settings, with greater interest in AAE production in less formal settings. When LLMs were appropriately prompted and provided in context examples, our participants found their outputs to have a level of AAE authenticity on par with transcripts of Black American speech. Select code and data for our project can be found here: \url{https://github.com/smelliecat/AAEMime.git}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sandoval-etal-2025-llm">
<titleInfo>
<title>My LLM might Mimic AAE - But When Should It?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="given">Camille</namePart>
<namePart type="family">Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christabel</namePart>
<namePart type="family">Acquaye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kwesi</namePart>
<namePart type="given">Adu</namePart>
<namePart type="family">Cobbina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Nayeem</namePart>
<namePart type="family">Teli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hal</namePart>
<namePart type="given">Daumé</namePart>
<namePart type="family">Iii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>We examine the representation of African American English (AAE) in large language models (LLMs), exploring (a) the perceptions Black Americans have of how effective these technologies are at producing authentic AAE, and (b) in what contexts Black Americans find this desirable. Through both a survey of Black Americans (n= 104) and annotation of LLM-produced AAE by Black Americans (n= 228), we find that Black Americans favor choice and autonomy in determining when AAE is appropriate in LLM output. They tend to prefer that LLMs default to communicating in Mainstream U.S. English in formal settings, with greater interest in AAE production in less formal settings. When LLMs were appropriately prompted and provided in context examples, our participants found their outputs to have a level of AAE authenticity on par with transcripts of Black American speech. Select code and data for our project can be found here: https://github.com/smelliecat/AAEMime.git</abstract>
<identifier type="citekey">sandoval-etal-2025-llm</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.273</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.273/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5277</start>
<end>5302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T My LLM might Mimic AAE - But When Should It?
%A Sandoval, Sandra Camille
%A Acquaye, Christabel
%A Cobbina, Kwesi Adu
%A Teli, Mohammad Nayeem
%A Iii, Hal Daumé
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F sandoval-etal-2025-llm
%X We examine the representation of African American English (AAE) in large language models (LLMs), exploring (a) the perceptions Black Americans have of how effective these technologies are at producing authentic AAE, and (b) in what contexts Black Americans find this desirable. Through both a survey of Black Americans (n= 104) and annotation of LLM-produced AAE by Black Americans (n= 228), we find that Black Americans favor choice and autonomy in determining when AAE is appropriate in LLM output. They tend to prefer that LLMs default to communicating in Mainstream U.S. English in formal settings, with greater interest in AAE production in less formal settings. When LLMs were appropriately prompted and provided in context examples, our participants found their outputs to have a level of AAE authenticity on par with transcripts of Black American speech. Select code and data for our project can be found here: https://github.com/smelliecat/AAEMime.git
%R 10.18653/v1/2025.naacl-long.273
%U https://aclanthology.org/2025.naacl-long.273/
%U https://doi.org/10.18653/v1/2025.naacl-long.273
%P 5277-5302
Markdown (Informal)
[My LLM might Mimic AAE - But When Should It?](https://aclanthology.org/2025.naacl-long.273/) (Sandoval et al., NAACL 2025)
ACL
- Sandra Camille Sandoval, Christabel Acquaye, Kwesi Adu Cobbina, Mohammad Nayeem Teli, and Hal Daumé Iii. 2025. My LLM might Mimic AAE - But When Should It?. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5277–5302, Albuquerque, New Mexico. Association for Computational Linguistics.