Nature’s New Breakthrough: Control Human Language Network via Large Language Model

In a new breakthrough paper Driving and suppressing the human language network using large language models, a research team from Massachusetts Institute of Technology, MIT-IBM Watson AI Lab, University of Minnesota and Harvard University leverages a GPT-based encoding model to identify sentences predicted to elicit specific responses within the human language network.

ai artificial intelligence control deep-neural-networks driving encoding gpt harvard harvard university human ibm identify institute lab language language model language models large language large language model large language models machine learning machine learning & data science massachusetts massachusetts institute of technology minnesota mit mit-ibm watson ai lab ml nature network paper research research team responses team technology university via watson