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.
@article{arxiv.2304.03728,
title = {Interpretable Unified Language Checking},
author = {Tianhua Zhang and Hongyin Luo and Yung-Sung Chuang and Wei Fang and Luc Gaitskell and Thomas Hartvigsen and Xixin Wu and Danny Fox and Helen Meng and James Glass},
journal= {arXiv preprint arXiv:2304.03728},
year = {2023}
}