可解释的统一语言检查
Interpretable Unified Language Checking
AI总结：
本文提出可解释的统一语言检查方法UniLC，通过简单的少样本统一提示集，使LLMs在事实核查、刻板印象和仇恨言论检测等多任务上超越全监督基线，成为自适应且可解释的检测工具。
摘要：
尽管近期人们对大型语言模型（LLMs）生成的不良行为（包括非事实性、偏见性和仇恨性语言）存在担忧，但我们发现，基于自然和社会知识的潜在表示，LLMs本身就是多任务语言检查器。我们提出了一种面向人类和机器生成语言的可解释统一语言检查（UniLC）方法，旨在检查语言输入是否真实且公平。尽管公平性和事实核查任务此前一直由专用模型分别处理，但我们发现，通过一套简单的、少样本的、统一的提示集，LLMs在结合事实核查、刻板印象检测和仇恨言论检测的任务上能够取得高性能。利用本文提出的“1/2样本”多任务语言检查方法，GPT3.5-turbo模型在多项语言任务上优于完全监督的基线模型。这一简单方法及其结果表明，基于强大的潜在知识表示，LLM可以成为检测虚假信息、刻板印象和仇恨言论的自适应且可解释的工具。
英文摘要：
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natural and social knowledge. We present an interpretable, unified, language checking (UniLC) method for both human and machine-generated language that aims to check if language input is factual and fair. While fairness and fact-checking tasks have been handled separately with dedicated models, we find that LLMs can achieve high performance on a combination of fact-checking, stereotype detection, and hate speech detection tasks with a simple, few-shot, unified set of prompts. With the ``1/2-shot'' multi-task language checking method proposed in this work, the GPT3.5-turbo model outperforms fully supervised baselines on several language tasks. The simple approach and results suggest that based on strong latent knowledge representations, an LLM can be an adaptive and explainable tool for detecting misinformation, stereotypes, and hate speech.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
