2 papers
cs.CL2024
Learning to Decode Collaboratively with Multiple Language Models
Shannon Zejiang Shen, Hunter Lang, Bailin Wang +2
We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates…
cs.LG2024
Theoretical Analysis of Weak-to-Strong Generalization
Hunter Lang, David Sontag, Aravindan Vijayaraghavan
Strong student models can learn from weaker teachers: when trained on the predictions of a weaker model, a strong pretrained student can learn to correct the weak model's errors an…