PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes

2026-06-16

AI Summary

This study addresses the pervasive challenge in intelligent assistants of insufficient understanding of incrementally elliptical commands within shared contexts, which often leads to referential ambiguity and intent misinterpretation. To tackle this issue, the work presents the first systematic modeling of elliptical expressions in real-world home environments and introduces PEC-Home, the inaugural dataset of progressive elliptical instructions tailored for smart homes. The authors evaluate state-of-the-art approaches by integrating large language models (e.g., GPT-4o), dialogue history retrieval mechanisms, and simulated environment annotation techniques. Experimental results demonstrate that current systems exhibit significantly lower execution accuracy when relying solely on elliptical instructions compared to complete ones, and even with access to dialogue history, a substantial performance gap persists—highlighting the critical challenge of context-aware comprehension and underscoring the research value of the proposed dataset.

Abstract

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.}.

Problem

• elliptical commands
• smart homes
• referential ambiguity
• intention ambiguity
• natural language interaction

Innovation

• elliptical commands
• smart homes
• large language models
• referential ambiguity
• intention ambiguity