PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
Quick Answer
PEC-Home introduces a dataset for interpreting progressively elliptical commands in smart homes, addressing referential and intention ambiguities.
Quick Take
Experiments with like GPT-4o reveal that current home assistants struggle with elliptical commands, achieving less than optimal execution accuracy compared to complete commands.
Key Points
- PEC-Home is the first dataset for progressively elliptical commands in smart homes.
- Elliptical commands lead to referential ambiguity among multiple users.
- User preferences cause intention ambiguity, complicating command interpretation.
- Experiments show LLMs like GPT-4o struggle with elliptical command execution.
- Execution accuracy remains below that of complete commands, even with dialogue history.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Recent advancements in Large Language Models (LLMs) have empowered home assistants with natural language interaction capabilities. However, current assistants overlook the progressive omission that occurs in human dialogue as shared context accumulates, leading to more elliptical expressions for efficient communication. Thus, current assistants still struggle to interpret such elliptical expressions accurately, which limits their effectiveness in real-world applications. In practical smart home scenarios, assistants face two major challenges caused by elliptical commands: (1) referential ambiguity caused by different environmental expectations among multiple users; and (2) intention ambiguity resulting from user preferences that evolve over time or change with the environment. To address these challenges, we introduce PEC-Home, the first simulated home dataset specifically designed for interpreting progressively elliptical commands in smart homes. Extensive experiments on various LLMs, including GPT-4o, show that existing home assistants struggle to execute user-intended operations based solely on elliptical commands. Even when equipped with tools for storing and retrieving user dialogue history, execution accuracy remains below that achieved with complete commands.}.
| Comments: | Accepted by ACL 2026 Findings |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.18636 [cs.CL] |
| (or arXiv:2606.18636v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.18636 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yingyu Shan [view email]
[v1]
Wed, 17 Jun 2026 03:17:34 UTC (1,170 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.