ΑΙhub.org
 

Linguistic bias in ChatGPT: Language models reinforce dialect discrimination


by
30 September 2024



share this:

Sample language model responses to different varieties of English and native speaker reactions.

By Eve Fleisig, Genevieve Smith, Madeline Bossi, Ishita Rustagi, Xavier Yin, and Dan Klein

ChatGPT does amazingly well at communicating with people in English. But whose English?

Only 15% of ChatGPT users are from the US, where Standard American English is the default. But the model is also commonly used in countries and communities where people speak other varieties of English. Over 1 billion people around the world speak varieties such as Indian English, Nigerian English, Irish English, and African-American English.

Speakers of these non-“standard” varieties often face discrimination in the real world. They’ve been told that the way they speak is unprofessional or incorrect, discredited as witnesses, and denied housing–despite extensive research indicating that all language varieties are equally complex and legitimate. Discriminating against the way someone speaks is often a proxy for discriminating against their race, ethnicity, or nationality. What if ChatGPT exacerbates this discrimination?

To answer this question, our recent paper examines how ChatGPT’s behavior changes in response to text in different varieties of English. We found that ChatGPT responses exhibit consistent and pervasive biases against non-“standard” varieties, including increased stereotyping and demeaning content, poorer comprehension, and condescending responses.

Our study

We prompted both GPT-3.5 Turbo and GPT-4 with text in ten varieties of English: two “standard” varieties, Standard American English (SAE) and Standard British English (SBE); and eight non-“standard” varieties, African-American, Indian, Irish, Jamaican, Kenyan, Nigerian, Scottish, and Singaporean English. Then, we compared the language model responses to the “standard” varieties and the non-“standard” varieties.

First, we wanted to know whether linguistic features of a variety that are present in the prompt would be retained in GPT-3.5 Turbo responses to that prompt. We annotated the prompts and model responses for linguistic features of each variety and whether they used American or British spelling (e.g., “colour” or “practise”). This helps us understand when ChatGPT imitates or doesn’t imitate a variety, and what factors might influence the degree of imitation.

Then, we had native speakers of each of the varieties rate model responses for different qualities, both positive (like warmth, comprehension, and naturalness) and negative (like stereotyping, demeaning content, or condescension). Here, we included the original GPT-3.5 responses, plus responses from GPT-3.5 and GPT-4 where the models were told to imitate the style of the input.

Results

We expected ChatGPT to produce Standard American English by default: the model was developed in the US, and Standard American English is likely the best-represented variety in its training data. We indeed found that model responses retain features of SAE far more than any non-“standard” dialect (by a margin of over 60%). But surprisingly, the model does imitate other varieties of English, though not consistently. In fact, it imitates varieties with more speakers (such as Nigerian and Indian English) more often than varieties with fewer speakers (such as Jamaican English). That suggests that the training data composition influences responses to non-“standard” dialects.

ChatGPT also defaults to American conventions in ways that could frustrate non-American users. For example, model responses to inputs with British spelling (the default in most non-US countries) almost universally revert to American spelling. That’s a substantial fraction of ChatGPT’s userbase likely hindered by ChatGPT’s refusal to accommodate local writing conventions.

Model responses are consistently biased against non-“standard” varieties. Default GPT-3.5 responses to non-“standard” varieties consistently exhibit a range of issues: stereotyping (19% worse than for “standard” varieties), demeaning content (25% worse), lack of comprehension (9% worse), and condescending responses (15% worse).

Native speaker ratings of model responses. Responses to non-”standard” varieties (blue) were rated as worse than responses to “standard” varieties (orange) in terms of stereotyping (19% worse), demeaning content (25% worse), comprehension (9% worse), naturalness (8% worse), and condescension (15% worse).

When GPT-3.5 is prompted to imitate the input dialect, the responses exacerbate stereotyping content (9% worse) and lack of comprehension (6% worse). GPT-4 is a newer, more powerful model than GPT-3.5, so we’d hope that it would improve over GPT-3.5. But although GPT-4 responses imitating the input improve on GPT-3.5 in terms of warmth, comprehension, and friendliness, they exacerbate stereotyping (14% worse than GPT-3.5 for minoritized varieties). That suggests that larger, newer models don’t automatically solve dialect discrimination: in fact, they might make it worse.

Implications

ChatGPT can perpetuate linguistic discrimination toward speakers of non-“standard” varieties. If these users have trouble getting ChatGPT to understand them, it’s harder for them to use these tools. That can reinforce barriers against speakers of non-“standard” varieties as AI models become increasingly used in daily life.

Moreover, stereotyping and demeaning responses perpetuate ideas that speakers of non-“standard” varieties speak less correctly and are less deserving of respect. As language model usage increases globally, these tools risk reinforcing power dynamics and amplifying inequalities that harm minoritized language communities.

Learn more here: [ paper ]


This article was initially published on the BAIR blog, and appears here with the authors’ permission.



tags:


BAIR blog




            AIhub is supported by:


Related posts :



Everything you say to an Alexa speaker will now be sent to Amazon

  04 Apr 2025
This change was implemented on 28 March 2025.

End-to-end data-driven weather prediction

  04 Apr 2025
A new AI weather prediction system, developed by a team of researchers, can deliver accurate forecasts.

Interview with Joseph Marvin Imperial: aligning generative AI with technical standards

  02 Apr 2025
Joseph tells us about his PhD research so far and his experience at the AAAI 2025 Doctoral Consortium.

Forthcoming machine learning and AI seminars: April 2025 edition

  01 Apr 2025
A list of free-to-attend AI-related seminars that are scheduled to take place between 1 April and 31 May 2025.

AI can be a powerful tool for scientists. But it can also fuel research misconduct

  31 Mar 2025
While AI is allowing scientists to make technological breakthroughs, there’s also a darker side to the use of AI in science: scientific misconduct is on the rise.
monthly digest

AIhub monthly digest: March 2025 – human-allied AI, differential privacy, and social media microtargeting

  28 Mar 2025
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.

AI ring tracks spelled words in American Sign Language

  27 Mar 2025
In its current form, SpellRing could be used to enter text into computers or smartphones via fingerspelling.

How AI images are ‘flattening’ Indigenous cultures – creating a new form of tech colonialism

  26 Mar 2025
AI-generated stock images that claim to depict “Indigenous Australians”, don’t resemble Aboriginal and Torres Strait Islander peoples.




AIhub is supported by:






©2024 - Association for the Understanding of Artificial Intelligence


 












©2021 - ROBOTS Association