Perplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Student Reinforcement Learning Method

Perplexity, along with NVIDIA team, has introduced JOLT, a new post-training method for language models. JOLT stands for Joint On-policy Learning and Teaching. It trains a single model in 2 roles. The teacher sees privileged information; the student does not. The key change is that the teacher is trained too, so its feedback stays usable. On MATH,... Weiterlesen: Perplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Stu…