August 19, 2023
2 mins read

ChatGPT is politically biased, finds study

These multiple responses were then put through a 1000-repetition ‘bootstrap’ (a method of re-sampling the original data) to further increase the reliability of the inferences drawn from the generated text…reports Asian Lite News

OpenAI’s artificial intelligence chatbot ChatGPT has a significant and systemic Left-wing bias, according to a new study.

Published in the journal ‘Public Choice’, the findings show that ChatGPT’s responses favour the Democrats in the US, the Labour Party in the UK, and President Lula da Silva of the Workers’ Party in Brazil.

Concerns of an inbuilt political bias in ChatGPT have been raised previously but this is the first large scale study using a consistent, evidenced-based analysis. “With the growing use by the public of AI-powered systems to find out facts and create new content, it is important that the output of popular platforms such as ChatGPT is as impartial as possible,” said lead author Fabio Motoki of Norwich Business School at the University of East Anglia in the UK.

“The presence of political bias can influence user views and has potential implications for political and electoral processes. Our findings reinforce concerns that AI systems could replicate, or even amplify, the existing challenges posed by the Internet and social media,” Motoki said. The researchers developed an innovative new method to test ChatGPT’s political neutrality.

The platform was asked to impersonate individuals from across the political spectrum while answering a series of more than 60 ideological questions.

The responses were then compared to the platform’s default answers to the same set of questions — allowing the researchers to measure the degree to which ChatGPT’s responses were associated with a particular political stance. To overcome difficulties caused by the inherent randomness of ‘large language models’ that power AI platforms such as ChatGPT, each question was asked 100 times and the different responses were collected.

These multiple responses were then put through a 1000-repetition ‘bootstrap’ (a method of re-sampling the original data) to further increase the reliability of the inferences drawn from the generated text.

“Due to the model’s randomness, even when impersonating a Democrat, sometimes ChatGPT answers would lean towards the right of the political spectrum,” said co-author Victor Rodrigues.  A number of further tests were undertaken to ensure the method was as rigorous as possible. In a ‘dose-response test’ ChatGPT was asked to impersonate radical political positions.

In a ‘placebo test’, it was asked politically-neutral questions. And in a ‘profession-politics alignment test’, it was asked to impersonate different types of professionals.

In addition to political bias, the tool can be used to measure other types of biases in ChatGPT’s responses. While the research project did not set out to determine the reasons for the political bias, the findings did point towards two potential sources.

The first was the training dataset — which may have biases within it, or added to it by the human developers, which the developers’ ‘cleaning’ procedure had failed to remove. The second potential source was the algorithm itself, which may be amplifying existing biases in the training data.

ALSO READ-ChatGPT maker OpenAI likely to go bankrupt by 2024

Previous Story

‘China, Russia aiming to steal tech from US space companies’

Next Story

DeSantis slips in GOP Primary

Latest from Tech LITE

India to host AI impact summit 2026

India to host 2026 AI Summit, boosting global dialogue on safe, inclusive tech, while Gujarat launches state-wide AI plan for governance, growth, and public welfare. India is set to host the AI

LLMs solve wargaming challenge

Dstl and Frazer-Nash demonstrate how large language models (LLMs) can solve the challenge of getting through large amounts of wargaming data Analysts at the Defence Science and Technology Laboratory (Dstl) have demonstrated

Apple Appoints Sabih Khan as New COO

Khan will take over from Jeff Williams, who is stepping down from the role this month and will retire later this year…reports Asian Lite News Apple has announced that Sabih Khan, an
Go toTop

Don't Miss

Italy bans ChatGPT citing data breach

Italy’s privacy watchdog said a data breach was reported affecting

Musk’s ‘TruthGPT’ to rival ChatGPT

The revelation comes as the billionaire has created a new