Nico Daheim

Parameter-space exploration can significantly enhance LLM reinforcement learning, yielding better performance with fewer training errors than traditional methods.

Risk-averse decision-making can backfire, leading to generic outputs, while Bayesian methods enhance LLM performance in high-stakes tasks like tutoring and peer review.

LLMs that excel at math don't necessarily make good math tutors, revealing a surprising trade-off between subject matter expertise and pedagogical skill.