MIT Finds a Simple Word Prefix Boosts AI Math Scores by 36 Points
A multi-institution study shows base models can match RL-trained counterparts on math and code simply by prefilling the right opening tokens, with effects traceable to training data.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
A multi-institution study shows base models can match RL-trained counterparts on math and code simply by prefilling the right opening tokens, with effects traceable to training data.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.