Self-refining methods for LLMs rely on prompting at each intermediate reasoning step and the model's own reasoning capabilities to correct itself, which can lead to unreliable performance gains according to Huang et al. (2023) and Li et al. (2024).

Authors

• Person: Not available Organization: medRxiv
  Medical Hallucination in Foundation Models and Their ...

Sources

• Medical Hallucination in Foundation Models and Their ... www.medrxiv.org medRxiv via serper

Referenced by nodes (1)

• Large Language Models concept