HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices
This addresses the challenge of making LLM-based smart home assistants more robust for real-world use, though it is incremental as it focuses on benchmarking rather than solving the underlying issues.
The paper tackles the problem of evaluating LLMs in smart home scenarios involving invalid or multi-device instructions, introducing HomeBench as the first dataset for this purpose, and finds that even advanced models like GPT-4o achieve a 0.0% success rate in invalid multi-device cases.
Large language models (LLMs) have the potential to revolutionize smart home assistants by enhancing their ability to accurately understand user needs and respond appropriately, which is extremely beneficial for building a smarter home environment. While recent studies have explored integrating LLMs into smart home systems, they primarily focus on handling straightforward, valid single-device operation instructions. However, real-world scenarios are far more complex and often involve users issuing invalid instructions or controlling multiple devices simultaneously. These have two main challenges: LLMs must accurately identify and rectify errors in user instructions and execute multiple user instructions perfectly. To address these challenges and advance the development of LLM-based smart home assistants, we introduce HomeBench, the first smart home dataset with valid and invalid instructions across single and multiple devices in this paper. We have experimental results on 13 distinct LLMs; e.g., GPT-4o achieves only a 0.0% success rate in the scenario of invalid multi-device instructions, revealing that the existing state-of-the-art LLMs still cannot perform well in this situation even with the help of in-context learning, retrieval-augmented generation, and fine-tuning. Our code and dataset are publicly available at https://github.com/BITHLP/HomeBench.