Rik Bose
@infiniterik.bsky.social
Senior Researcher in agentic AI at the Johns Hopkins Applied Physics Lab
Checkout our recent #arxiv paper on assessing alignment between humans and #AI. Turns out #LLMs are not so great at emulating the diversity of human populations!
#generativeai #alignment
arxiv.org/abs/2412.00577
#generativeai #alignment
arxiv.org/abs/2412.00577
Turing Representational Similarity Analysis (RSA): A Flexible Method for Measuring Alignment Between Human and Artificial Intelligence
As we consider entrusting Large Language Models (LLMs) with key societal and decision-making roles, measuring their alignment with human cognition becomes critical. This requires methods that can asse...
arxiv.org
December 3, 2024 at 5:33 PM
Checkout our recent #arxiv paper on assessing alignment between humans and #AI. Turns out #LLMs are not so great at emulating the diversity of human populations!
#generativeai #alignment
arxiv.org/abs/2412.00577
#generativeai #alignment
arxiv.org/abs/2412.00577