Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge, leading to potentially outdated or inaccurate responses. This problem becomes even more challenging when dealing with multi-hop questions, since they require LLMs to update and integrate multiple knowledge pieces relevant to the questions. To tackle the problem, we propose the Retrieval-Augmented model Editing (RAE) framework for multi-hop question answering. RAE first retrieves edited facts and then refines the language model through in-context learning. Specifically, our retrieval approach, based on mutual information maximization, leverages the reasoning abilities of LLMs to identify chain facts that traditional similarity-based searches might miss. In addition, our framework includes a pruning strategy to eliminate redundant information from the retrieved facts, which enhances the editing accuracy and mitigates the hallucination problem. Our framework is supported by theoretical justification for its fact retrieval efficacy. Finally, comprehensive evaluation across various LLMs validates RAE's ability in providing accurate answers with updated knowledge. Our code is available at: https://github.com/sycny/RAE.

Photovoltaic array produces massive running data, and such data are time series of strong coupling features with each other. In addition, photovoltaic output data has a strong fluctuating and nonlinear feature; it brings extra difficulty to photovoltaic array fault feature extraction and its fault diagnosis. To solve these problems, this article proposes a fault diagnosis method using the time series features for photovoltaic array. The features of the photovoltaic array output are described in this article. From the perspective of distance analysis and similarity analysis, this article proposes a feature extraction method for photovoltaic array output time series, and features of output time series under different fault conditions are analyzed. Taking similarity index and distance index as input, the fuzzy system is built for identifying faults for photovoltaic array. The operational data analysis shows that the time series feature indexes proposed can successfully characterize different fault types, and this method can effectively diagnose typical faults of photovoltaic array.