Filter Options
Date
Image
The “Steerable Scene Generation” approach creates digital scenes of things like kitchens, living rooms, and restaurants that engineers can use to simulate lots of real-world robot interactions and scenarios (Credit: Image courtesy of the researchers).
CSAIL article

Chatbots like ChatGPT and Claude have experienced a meteoric rise in usage over the past three years because they can help you with a wide range of tasks. Whether you’re writing Shakespearean sonnets, debugging code, or need an answer to an obscure trivia question, artificial intelligence (AI) systems seem to have you covered. The source of this versatility? Billions or even trillions of textual data points across the Internet.

Image
The researchers ran nearly daily queries across 12 state-of-the-art models on more than 12,000 carefully constructed prompts, generating a dataset with over 16 million responses from LLMs (Credit: Alex Shipps/MIT CSAIL, using ChatGPT for humanoid drawing and Pixabay for background image).
CSAIL article

In the months leading up to the 2024 U.S. presidential election, a team of researchers at MIT CSAIL, MIT Sloan, MIT LIDS, set out to answer a question no one had fully explored: how do large language models (LLMs) respond to questions about the election? Over four months, from July through November, the team ran nearly daily queries across 12 state-of-the-art models on more than 12,000 carefully constructed prompts, generating a dataset with over 16 million responses from LLMs, to help answer this question.