Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Yang, Zhao, Yong, Li, Moxin, Ng, See-Kiong, Chua, Tat-Seng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912054652174336
author Deng, Yang
Zhao, Yong
Li, Moxin
Ng, See-Kiong
Chua, Tat-Seng
author_facet Deng, Yang
Zhao, Yong
Li, Moxin
Ng, See-Kiong
Chua, Tat-Seng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15062
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
Deng, Yang
Zhao, Yong
Li, Moxin
Ng, See-Kiong
Chua, Tat-Seng
Computation and Language
Machine Learning
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.
title Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2402.15062