White Paper On Testing Wisdom In AI Launched At IIT Ropar
Titled“Beyond Intelligence: Defining and Measuring Wisdom for AI”, it explores how wisdom in artificial intelligence can be defined, measured and tested, drawing upon Dr Shivanand's interpretation of the Shiv Sutras and India's classical texts on the human mind.
Addressing the media, Dr Shivanand said,“The initiative highlights the growing need to assess AI systems not merely based on their intelligence and technical capabilities but also on their ability to exercise sound judgement and provide responsible guidance.”
“While AI systems can now pass professional examinations and perform well in emotional intelligence assessments, they often tend to tell users what they want to hear rather than what is genuinely beneficial for them.”
Citing a study published in the journal Science this year, the white paper“points out that leading AI systems, when asked for everyday advice, sided with users approximately 49 per cent more often than humans did”.
The White Paper argues that while AI has made significant advances in intelligence, it still lacks an essential human attribute: wisdom.
To address this gap, the authors have introduced a framework called HEED to measure wisdom in AI systems.
As part of the initiative, Dr Shivanand is providing seed funding for an open call inviting independent researchers to test the proposed framework.
A committee comprising independent members will select research teams to evaluate the model and develop HEED Bench, an open benchmark for measuring wisdom in AI, which will be made available to AI developers worldwide.
Legal Disclaimer:
MENAFN provides the
information “as is” without warranty of any kind. We do not accept
any responsibility or liability for the accuracy, content, images,
videos, licenses, completeness, legality, or reliability of the information
contained in this article. If you have any complaints or copyright
issues related to this article, kindly contact the provider above.
Comments
No comment