Researchers reduce bias in AI models while preserving or improving accuracy
A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.
Learn about artificial intelligence, GPT usage, prompt engineering and other technology news and updates from Land of GPT. The site aggregates articles from official RSS feeds under their original authorship. Each article has a do-follow link to the original source.
A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.
This new tool offers an easier way for people to analyze complex tabular data.
The SPARROW algorithm automatically identifies the best molecules to test as potential new medicines, given the vast number of factors affecting each choice.
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
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 researchers plan to search for proteins that could be used to measure electrical activity in the brain.
The new approach “nudges” existing climate simulations closer to future reality.
MIT CSAIL researchers develop advanced machine-learning models that outperform current methods in detecting pancreatic ductal adenocarcinoma.
A multimodal system uses models trained on language, vision, and action data to help robots develop and execute plans for household, construction, and manufacturing tasks.