"Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process

TL;DR

This paper presents ETHICSSUITE, a comprehensive testing framework, and a suggest-critic-reflect process for automatically detecting and repairing unethical suggestions made by large language models in real-time.

Contribution

It introduces the first automated testing and repair framework for unethical LLM suggestions, including a novel OTF repair scheme applicable to black-box APIs.

Findings

Uncovered 109,824 unethical suggestions across seven LLMs.

OTF repair scheme effectively repairs a significant portion of unethical outputs.

Demonstrated real-time repair capability with Llama-13B and ChatGPT.

Abstract

As the popularity of large language models (LLMs) soars across various applications, ensuring their alignment with human values has become a paramount concern. In particular, given that LLMs have great potential to serve as general-purpose AI assistants in daily life, their subtly unethical suggestions become a serious and real concern. Tackling the challenge of automatically testing and repairing unethical suggestions is thus demanding. This paper introduces the first framework for testing and repairing unethical suggestions made by LLMs. We first propose ETHICSSUITE, a test suite that presents complex, contextualized, and realistic moral scenarios to test LLMs. We then propose a novel suggest-critic-reflect (SCR) process, serving as an automated test oracle to detect unethical suggestions. We recast deciding if LLMs yield unethical suggestions (a hard problem; often requiring human expertise and costly to decide) into a PCR task that can be automatically checked for violation. Moreover, we propose a novel on-the-fly (OTF) repairing scheme that repairs unethical suggestions made by LLMs in real-time. The OTF scheme is applicable to LLMs in a black-box API setting with moderate cost. With ETHICSSUITE, our study on seven popular LLMs (e.g., ChatGPT, GPT-4) uncovers in total 109,824 unethical suggestions. We apply our OTF scheme on two LLMs (Llama-13B and ChatGPT), which generates valid repair to a considerable amount of unethical ones, paving the way for more ethically conscious LLMs.