Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us

2026-03-16

AI Summary

结合计算论证与大语言模型，通过论证框架挖掘、合成与推理，实现可辩论、可修正的人机协同决策。

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Computational argumentation offers formal frameworks for transparent, verifiable reasoning but has traditionally been limited by its reliance on domain-specific information and extensive feature engineering. In contrast, LLMs excel at processing unstructured text, yet their opaque nature makes their reasoning difficult to evaluate and trust. We argue that the convergence of these fields will lay the foundation for a new paradigm: Argumentative Human-AI Decision-Making. We analyze how the synergy of argumentation framework mining, argumentation framework synthesis, and argumentative reasoning enables agents that do not just justify decisions, but engage in dialectical processes where decisions are contestable and revisable -- reasoning with humans rather than for them. This convergence of computational argumentation and LLMs is essential for human-aware, trustworthy AI in high-stakes domains.

Problem

• Argumentative Human-AI Decision-Making
• Computational Argumentation
• Large Language Models
• Trustworthy AI
• Dialectical Reasoning

Innovation

• computational argumentation
• large language models
• argumentative reasoning
• human-AI collaboration
• trustworthy AI