# Toward Ownership Understanding of Objects: Active Question Generation with Large Language Model and Probabilistic Generative Model

arXiv: https://arxiv.org/abs/2509.12754 · HTML: https://mlsanity.com/paper/2509.12754/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Open-vocabulary Queryable Scene Representations for Real World Planning](https://mlsanity.com/paper/2209.09874/) (2022)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks](https://mlsanity.com/paper/1301.3853/) (2013)
- [Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation](https://mlsanity.com/paper/2310.07968/) (2023)
- [CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents](https://mlsanity.com/paper/2306.10376/) (2023)
- [APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs](https://mlsanity.com/paper/2410.19656/) (2024)
- [K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition](https://mlsanity.com/paper/2203.07890/) (2022)
- [Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot](https://mlsanity.com/paper/2111.11099/) (2021)
- [Multimodal Hierarchical Dirichlet Process-based Active Perception](https://mlsanity.com/paper/1510.00331/) (2015)
- [That's Mine! Learning Ownership Relations and Norms for Robots](https://mlsanity.com/paper/1812.02576/) (2018)
- [Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation](https://mlsanity.com/paper/2211.10934/) (2022)
- [Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions](https://mlsanity.com/paper/2508.16143/) (2025)

## Built on by (most cited first, 1 of 1)

- [Who Owns That? Evaluating Ownership Intuitions in Large Language Models](https://mlsanity.com/paper/2609.39483/) (2026)

## Abstract (arXiv)

Robots operating in domestic and office environments must understand object ownership to correctly execute instructions such as ``Bring me my cup.'' However, ownership cannot be reliably inferred from visual features alone. To address this gap, we propose Active Ownership Learning (ActOwL), a framework that enables robots to actively generate and ask ownership-related questions to users. ActOwL employs a probabilistic generative model to select questions that maximize information gain, thereby acquiring ownership knowledge efficiently to improve learning efficiency. Additionally, by leveraging commonsense knowledge from Large Language Models (LLM), objects are pre-classified as either shared or owned, and only owned objects are targeted for questioning. Through experiments in a simulated home environment and a real-world laboratory setting, ActOwL achieved significantly higher ownership clustering accuracy with fewer questions than baseline methods. These findings demonstrate the effectiveness of combining active inference with LLM-guided commonsense reasoning, advancing the capability of robots to acquire ownership knowledge for practical and socially appropriate task execution.