Ever been asked a question you only knew part of the answer to? To give a more informed response, your best move would be to phone a friend with more knowledge on the subject. This collaborative ...

OctoTools uses a modular approach to tackle planning and reasoning tasks and can use any general-purpose LLM as its backbone ... also uses an optimization algorithm to select the best subset ...

Attempting to improve the model with supervised fine-tuning (SFT) typically requires a human or a stronger LLM to provide corrections. Methods which use SFT on self-generated corrections "often ...

InfoQ also covered LLM Attacks, an algorithm for constructing adversarial attacks, which was created to help researchers understand and prevent attacks. SafeDecoding works by constructing an ...