Don’t just say “I don’t know”! Self-aligning Large Language Models for responding to unknown questions with explanations

• المؤلفون الرئيسيون: DENG, Yang, ZHAO, Yong, LI, Moxin, NG, See-Kiong, CHUA, Tat-Seng
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: Large Language Models; LLMs; Unknown question response; Self-Align method; Artificial Intelligence and Robotics; Computer Sciences
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/9614; https://ink.library.smu.edu.sg/context/sis_research/article/10614/viewcontent/2402.15062v2.pdf

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ a two-stage class-aware self-augmentation approach to generate a large amount of unknown question-response data. Then we conduct disparity-driven self-curation to select qualified data for fine-tuning the LLM itself for aligning the responses to unknown questions as desired. Experimental results on two datasets across four types of unknown questions validate the superiority of the Self-Align method over existing baselines in terms of three types of task formulation.