Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid

TL;DR

Chats-Grid is an iterative retrieval-based Q&A system designed for smart grids, combining advanced query expansion, hybrid retrieval methods, and large language models to improve answer relevance, accuracy, and efficiency in dynamic, data-rich environments.

Contribution

The paper introduces a novel framework that integrates multi-source query expansion, hybrid retrieval, and large language model-based filtering for smart grid Q&A, enhancing performance over existing methods.

Findings

Improves relevance and accuracy by over 3.5%

Enhances retrieval effectiveness with hybrid BM25 and BGE methods

Demonstrates superior performance in smart grid applications

Abstract

With rapid advancements in artificial intelligence, question-answering (Q&A) systems have become essential in intelligent search engines, virtual assistants, and customer service platforms. However, in dynamic domains like smart grids, conventional retrieval-augmented generation(RAG) Q&A systems face challenges such as inadequate retrieval quality, irrelevant responses, and inefficiencies in handling large-scale, real-time data streams. This paper proposes an optimized iterative retrieval-based Q&A framework called Chats-Grid tailored for smart grid environments. In the pre-retrieval phase, Chats-Grid advanced query expansion ensures comprehensive coverage of diverse data sources, including sensor readings, meter records, and control system parameters. During retrieval, Best Matching 25(BM25) sparse retrieval and BAAI General Embedding(BGE) dense retrieval in Chats-Grid are combined to process vast, heterogeneous datasets effectively. Post-retrieval, a fine-tuned large language model uses prompt engineering to assess relevance, filter irrelevant results, and reorder documents based on contextual accuracy. The model further generates precise, context-aware answers, adhering to quality criteria and employing a self-checking mechanism for enhanced reliability. Experimental results demonstrate Chats-Grid's superiority over state-of-the-art methods in fidelity, contextual recall, relevance, and accuracy by 2.37%, 2.19%, and 3.58% respectively. This framework advances smart grid management by improving decision-making and user interactions, fostering resilient and adaptive smart grid infrastructures.