Artificial intelligence large language models used for writing and text-prediction are notoriously biased, but can be fine-tuned to become more inclusive.
Engineering and journalism researchers from the University of Southern California in the United States have teamed up to quantify and fix anti-queer bias in AI language models.
AI language models are capable of reading and writing text and predicting words in a sentence. But as most are trained by scraping text from the internet, they tend to repeat and amplify social biases. In fact as these models become more capable, their level of bias and toxicity increases.
Katy Felkner, a PhD student in computer science specialising in natural language processing says the problem of bias in language models is well documented.
“Large language models are very much a product of their training data. When the training data is scraped from the web with very minimal auditing, like most of the training data is today, you’re going to pick up a lot of the sort of nasty and hateful sentiments that are that are out there on the web.”
As part of the research, Felkner and team developed a new benchmark for measuring bias.
She says while there are generalised fairness measures available, there was limited research dealing with the issue of anti-queer and anti-trans bias in AI language models, and a lack of tailored benchmarks or metrics.
“I set out to do a more specific metric that would just address anti queer and anti trans bias but hopefully in a in a more nuanced and more holistic way.”
The project found that a popular model called BERT (short for bidirectional encoder representations from transformers) showed significant homophobic bias, measured through Felkner’s benchmark, which compares the likelihood that the model predicts heteronormative sentences versus sentences that include a queer relationship.
The team chose to focus on BERT as one of the first large language models to establish the power and potential of these technologies. There were practical reasons too as it was more accessible and practical to test and fine tune than other models.
By feeding more inclusive content like queer twitter and queer news, the research team successfully trained BERT to be less biased towards LGBTQI people.
The team was able to shift the bias score from 74% (using the off-the-shelf model) down to 55% through their fine-tuning.
She says the results mean that models “fine-tuned using our method are less likely to produce text that is toxic, harmful or mean, or homophobic or transphobic, and they are more likely to produce text that is is inclusive.”
Read more: The science says let transgender women play women’s sport
This is important because large language models are increasingly driving other kinds of downstream applications, like job advertisements or clinical applications.
“As these models are getting better and better, people are encountering more AI generated, or partially AI generated text in their daily lives. And so we want to make sure that those models are not are not going to inadvertently produce harmful outputs.”
The project was presented by Felkner at the Queer in AI workshop at the North American Chapter of the Association for Computational Linguistics (NAACL) conference and the team plans to publish a full conference paper.
For the next stage, the team hopes to crowd-source a wider set of perspectives from the queer community and audit more existing language models.
Busting homophobic, anti-queer bias in AI language models & Latest News Update
Busting homophobic, anti-queer bias in AI language models & More Live News
All this news that I have made and shared for you people, you will like it very much and in it we keep bringing topics for you people like every time so that you keep getting news information like trending topics and you It is our goal to be able to get
all kinds of news without going through us so that we can reach you the latest and best news for free so that you can move ahead further by getting the information of that news together with you. Later on, we will continue
to give information about more today world news update types of latest news through posts on our website so that you always keep moving forward in that news and whatever kind of information will be there, it will definitely be conveyed to you people.
Busting homophobic, anti-queer bias in AI language models & More News Today
All this news that I have brought up to you or will be the most different and best news that you people are not going to get anywhere, along with the information Trending News, Breaking News, Health News, Science News, Sports News, Entertainment News, Technology News, Business News, World News of this made available to all of you so that you are always connected with the news, stay ahead in the matter and keep getting today news all types of news for free till today so that you can get the news by getting it. Always take two steps forward
Credit Goes To News Website – This Original Content Owner News Website . This Is Not My Content So If You Want To Read Original Content You Can Follow Below Links