Enabling Weak LLMs to Judge Response Reliability via Meta Ranking

no code implementations • 19 Feb 2024 • Zijun Liu, Boqun Kou, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

In model cascading, we combine open- and closed-source LLMs to achieve performance comparable to GPT-4-turbo with lower costs.

Hallucination In-Context Learning