학술논문
Enabling Large Language Models to Think Twice When Its Answer Is Unreliable: A Case Study In Cancer Screening
Document Type
Conference
Author
Source
2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Bioinformatics and Biomedicine (BIBM), 2023 IEEE International Conference on. :4975-4977 Dec, 2023
Subject
Language
ISSN
2156-1133
Abstract
To enhance the accuracy and reliability of the response of large language models (LLMs) in professional domain-specific question answering, this paper proposes an approach to enhance the capabilities of LLMs by prompting them to "think twice." This methodology encourages a second-pass processing, allowing for deeper analysis and more refined outputs. We developed a prototype-logic-inspired query optimizer (PQO) to enhance the response of LLM. It refines initial queries using few-shot learning and self-reflection, leading to more insightful questions. Our experimental results show that the proposed approach obtains empirically validated answers.