Research map / Large language models / AI and society
The Utility of Explainable AI in Ad Hoc Human-Machine Teaming
Rohan R Paleja, Muyleng Ghuy, Nadun Ranawaka Arachchige, Reed Jensen, Matthew Gombolay
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add a short status explanation of the cobot policy | Human-machine team in Minecraft · Study 1, Level 2 SA | ability to comprehend the cobot's decision-making: p<0.05 | Improved |
| Add a decision-tree explanation of the cobot policy | Human-machine team in Minecraft · Study 1, Level 2 SA | ability to comprehend the cobot's decision-making: p<0.001 | Improved |
| Add a decision-tree explanation of the cobot policy | Human-machine team in Minecraft · Study 1, Level 3 SA | ability to project the cobot's behavior: p<0.05 | Improved |
| Add xAI support | Human-machine team in Minecraft · Study 1, Level 1 SA | perception of the environment | No clear effect |
| Add a short status explanation of the cobot policy | Novice human-machine teams · Minecraft house-building task, Study 2 | task completion time: p<0.05 | Improved |
| Add a decision-tree explanation rather than a short status explanation | Novice human-machine teams · Minecraft house-building task, Study 2 | task completion time: p<0.05 | Hurt |
| Add decision-tree support rather than no explanation | Novice human-machine teams · Minecraft house-building task, Study 2 | task completion time | No clear effect |
| Add xAI-based support | Expert human-machine teams · Minecraft house-building task, Study 2 | task completion time: t(33)=2.09;p<0.05 | Hurt |
| Display the complete hierarchical policy instead of only the low-level policy | Expert human-machine teams · Minecraft house-building task, Study 2 | task completion time: p<0.05 | Hurt |
| Vary policy information level | Novice human-machine teams · Minecraft house-building task, Study 2 | task completion time | No clear effect |
| Add a decision-tree explanation rather than no explanation | Human-machine teams · Study 2 subjective ratings | positive teammate traits: p<0.05 | Improved |
| Add a decision-tree explanation rather than no explanation | Human-machine teams · Study 2 subjective ratings | working alliance: p<0.05 | Improved |
Closest papers by meaning
- Autonomous Policy Explanations for Effective Human-Machine Teaming (AAAI 2024 · similarity 0.90)
- Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems (NeurIPS 2024 · similarity 0.90)
- Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics (NeurIPS 2024 · similarity 0.87)
- NestRL: A Nested Training Regime for Mutual Adaptation in Human–AI Teaming (NeurIPS 2026 · similarity 0.86)
- Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary (NeurIPS 2024 · similarity 0.86)
- When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
