Originally published in MIT News, March 25, 2024
Researchers demonstrate a technique that can be used to probe a model to see what it knows about new subjects.
Large language models, such as those that power popular artificial intelligence chatbots like ChatGPT, are incredibly complex. Even though these models are being used as tools in many areas, such as customer support, code generation, and language translation, scientists still don’t fully grasp how they work.
They found a surprising result: Large language models (LLMs) often use a very simple linear function to recover and decode stored facts. Moreover, the model uses the same decoding function for similar types of facts. Linear functions, equations with only two variables and no exponents, capture the straightforward, straight-line relationship between two variables.
The researchers showed that, by identifying linear functions for different facts, they can probe the model to see what it knows about new subjects, and where within the model that knowledge is stored.
To continue reading this article, click here.
You must be logged in to post a comment.
Hey, thank you!
Researchers demonstrate a technique that can be used to probe a model to see New York Knicks OVO Varsity Jacket