Summary of Explainable Human-ai Interaction: a Planning Perspective, by Sarath Sreedharan et al.
Explainable Human-AI Interaction: A Planning Perspective
by Sarath Sreedharan, Anagha Kulkarni, Subbarao Kambhampati
First submitted to arxiv on: 19 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach is proposed to enable AI systems to work synergistically with humans, focusing on explainability and human-AI interaction. The study draws on years of research in the lab to demonstrate how AI agents can utilize mental models to conform to or change human expectations through explanatory communication. In cooperative scenarios, this approach aims to facilitate effective collaboration between humans and AI. Furthermore, the same concepts can be applied to obfuscation and deception. The work builds connections to relevant research from other groups while primarily driven by the authors’ own research in these areas. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI systems need to be able to explain themselves to humans for effective interaction. To achieve this, AI agents must consider human mental models and use them to either conform to or change human expectations through communication. This approach can facilitate cooperation between humans and AI, but it can also be used for deception. The study draws on lab research and connects to other relevant work. |
