Behnam Bahrak

Guided LLM access not only improves reasoning skills but also leads to significantly better independent learning outcomes compared to unrestricted use.

Forget painstakingly curating evaluation datasets: this framework generates high-quality, multi-hop multiple-choice questions from knowledge graphs with tunable difficulty, all while slashing costs.

LLMs can often achieve the same accuracy with significantly shorter self-explanations, suggesting that current chain-of-thought reasoning is unnecessarily verbose.