Towards Dialogues for Joint Human-AI Reasoning and Value Alignment

TL;DR

This paper emphasizes the importance of human-AI inquiry dialogues, especially with large language models, to enhance joint reasoning and ensure AI decisions align with human values and ethics.

Contribution

It advocates shifting from persuasion to inquiry dialogues in logic-based models to improve joint human-AI reasoning and value alignment.

Findings

Highlights the role of inquiry dialogues in ethical decision-making.

Proposes a research roadmap for human-LLM joint reasoning.

Emphasizes the need for dialogue models that support value alignment.

Abstract

We argue that enabling human-AI dialogue, purposed to support joint reasoning (i.e., 'inquiry'), is important for ensuring that AI decision making is aligned with human values and preferences. In particular, we point to logic-based models of argumentation and dialogue, and suggest that the traditional focus on persuasion dialogues be replaced by a focus on inquiry dialogues, and the distinct challenges that joint inquiry raises. Given recent dramatic advances in the performance of large language models (LLMs), and the anticipated increase in their use for decision making, we provide a roadmap for research into inquiry dialogues for supporting joint human-LLM reasoning tasks that are ethically salient, and that thereby require that decisions are value aligned.