DeepAI AI Chat
Log In Sign Up

AiSocrates: Towards Answering Ethical Quandary Questions

by   Yejin Bang, et al.
The Hong Kong University of Science and Technology

Considerable advancements have been made in various NLP tasks based on the impressive power of large pre-trained language models (LLMs). These results have inspired efforts to understand the limits of LLMs so as to evaluate how far we are from achieving human level general natural language understanding. In this work, we challenge the capability of LLMs with the new task of Ethical Quandary Generative Question Answering. Ethical quandary questions are more challenging to address because multiple conflicting answers may exist to a single quandary. We propose a system, AiSocrates, that provides an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle. AiSocrates searches for different ethical principles applicable to the ethical quandary and generates an answer conditioned on the chosen principles through prompt-based few-shot learning. We also address safety concerns by providing a human controllability option in choosing ethical principles. We show that AiSocrates generates promising answers to ethical quandary questions with multiple perspectives, 6.92 written by human philosophers by one measure, but the system still needs improvement to match the coherence of human philosophers fully. We argue that AiSocrates is a promising step toward developing an NLP system that incorporates human values explicitly by prompt instructions. We are releasing the code for research purposes.


page 1

page 2

page 3

page 4


Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?

Is it possible to use natural language to intervene in a model's behavio...

Formalizing Preference Utilitarianism in Physical World Models

Most ethical work is done at a low level of formality. This makes practi...

The Ethical Need for Watermarks in Machine-Generated Language

Watermarks should be introduced in the natural language outputs of AI sy...

Towards Trustworthy AutoGrading of Short, Multi-lingual, Multi-type Answers

Autograding short textual answers has become much more feasible due to t...

Ethical Frameworks and Computer Security Trolley Problems: Foundations for Conversations

The computer security research community regularly tackles ethical quest...

Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy

In an effort to guarantee that machine learning model outputs conform wi...

Let's have a chat! A Conversation with ChatGPT: Technology, Applications, and Limitations

The emergence of an AI-powered chatbot that can generate human-like sent...