Towards Answering Open-ended Ethical Quandary Questions
This work addresses the problem of enhancing LLMs' ability to handle complex ethical dilemmas for applications in responsible NLP systems, though it is incremental in exploring a new task within existing frameworks.
The paper tackles the challenge of answering open-ended ethical quandary questions by proposing a model that uses prompt-based few-shot learning to generate answers conditioned on chosen ethical principles, achieving results that demonstrate LLMs' capability to provide deliberative responses instead of closed answers.
Considerable advancements have been made in various NLP tasks based on the impressive power of large language models (LLMs) and many NLP applications are deployed in our daily lives. 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 explore the current capability of LLMs in providing 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. We propose a model that 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 discuss the remaining challenges and ethical issues involved in this task and suggest the direction toward developing responsible NLP systems by incorporating human values explicitly.