A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.
Researchers create a curious machine-learning model that finds a wider variety of prompts for training a chatbot to avoid hateful or harmful output.
MIT CSAIL researchers are using ideas from game theory to improve the reliability of language generation in language models.
Screen-reader users can upload a dataset and create customized data representations that combine visualization, textual description, and sonification.
Researchers demonstrate a technique that can be used to probe a model to see what it knows about new subjects.
With help from a large language model, MIT engineers enabled robots to self-correct after missteps and carry on with their chores.
Researchers developed a simple yet effective solution for a puzzling problem that can worsen the performance of large language models such as ChatGPT.
PhD students interning with the MIT-IBM Watson AI Lab look to improve natural language usage.
Master's students Irene Terpstra ’23 and Rujul Gandhi ’22 use language to design new integrated circuits and make it understandable to robots.
MIT researchers develop a customized onboarding process that helps a human learn when a model’s advice is trustworthy.
/
6