Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us
#argumentative AI #human-AI decision-making #collaborative reasoning #AI transparency #decision support systems
📌 Key Takeaways
- Researchers propose argumentative AI systems that engage in reasoning dialogues with humans
- New approach shifts from AI making decisions for humans to collaborating through structured debate
- System aims to improve decision quality by exposing reasoning processes and assumptions
- Framework could enhance trust and transparency in human-AI collaboration
📖 Full Retelling
arXiv:2603.15946v1 Announce Type: new
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 Hum
🏷️ Themes
Human-AI Collaboration, Decision-Making Systems
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
arXiv:2603.15946v1 Announce Type: new
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 Hum
Read full article at source