- Published on January 11, 2022
- In AI Features
How bias creeps into large language models
According to DeepMind, unmodified LMs tend to assign high probabilities to exclusionary, biased, toxic, or sensitive utterances if such language is present in the training data.
- By Meeta Ramnani
Language models (LM) are optimised to mirror language systems. Therefore, it stands to reason that LMs might perpetuate stereotypes and biases hardwired into the natural language. When the training data is discriminatory, unfair, or toxic, optimisation leads to highly biased models.
Red flags
In 2019, researchers found racial bias in an algorithm used on over 200 million people in the US to predict the patients who need extra medical care. The system favoured whites over people of colour. The use of COMPAS (Correctional Offender Management Profiling for Alternative Sanctions) algorithm in US court systems projected double false positives for recidivism in black offenders (45%) as opposed to whites (23%). Amazon has scrapped its AI recruitment tool for its manifest sexist bias against
📣 Want to advertise in AIM? Book here
Meeta Ramnani
Meeta’s interest lies in finding out real practical applications of technology. At AIM, she writes stories that question the new inventions and the need to develop them. She believes that technology has and will continue to change the world very fast and that it is no more ‘cool’ to be ‘old-school’. If people don’t update themselves with the technology, they will surely be left behind.
Related Posts
Top 10 Companies That Crowned Hyderabad as India’s Greenfield GCC Leader in 2025
Telangana has attracted over 75 greenfield GCCs in 2025, compared with 40-plus in Karnataka.
The AI Coding Gold Rush Ends Where Harness Begins
“Only 30% of software engineering happens on the laptop. The real 70% starts after you commit the code,” says Jyoti
How Gradient-Boosting is Quietly Powering India’s Research Push
From groundwater and slopes to carbon sinks, tools like CatBoost are enabling Indian scientists to extract insights and drive sustainability.
India’s Data Centre Boom Is Running Into a Talent Wall
With capacity expected to more than double this decade, the industry is investing in training as graduates struggle to meet
This Firm Wants to be the ‘Next Big Disruptor’ in Networking
Arrcus positions itself as a horizontal software layer that can run across different types of networking hardware.
Will 2026 be the year of AI IPOs?
With CoreWeave’s listing and Fractal Analytics going for an IPO, an array of AI companies are now looking to raise
Fighting Deepfakes May Not Be a Technology Problem
Defenders must be active at all times, while attackers need only one opportunity.
India’s Data Centre Expansion Is Decentralising
Without compute buildup beyond metros, the next wave of digital adoption will be constrained
Download the easiest way to
stay informed
stay informed
