Cross-Document Multi-entity Question Answering (MEQA) demands the integration of scattered information across documents to resolve complex queries involving entities, relationships, and contextual dependencies.Although Large Language Models (LLMs) and Retrieval-augmented Generation (RAG) systems show promise, their performance on crossdocument MEQA remains underexplored due to the absence of tailored benchmarks.To address this gap, we introduce MEBench, a scalable multi-document, multi-entity benchmark designed to systematically evaluate LLMs' capacity to retrieve, consolidate, and reason over scattered and dense information.Our benchmark comprises 4,780 questions which are systematically categorized into three primary categories: Comparative Reasoning, Statistical Reasoning and Relational Reasoning, further divided into eight distinct types, ensuring broad coverage of real-world multi-entity reasoning scenarios.Our experiments on state-of-theart LLMs reveal critical limitations: even advanced models achieve only 59% accuracy on MEBench.Our benchmark emphasizes the importance of completeness and factual precision of information extraction in MEQA tasks, using Entity-Attributed F1 (EA-F1) metric for granular evaluation of entity-level correctness and attribution validity.MEBench not only highlights systemic weaknesses in current LLM frameworks but also provides a foundation for advancing robust, entity-aware QA architectures. 1

The integration of heterogeneous databases into a unified querying framework remains a critical challenge, particularly in resource-constrained environments. This paper presents a novel Small Language Model (SLM)-driven system that synergizes advancements in lightweight Retrieval-Augmented Generation (RAG) and semantic-aware data structuring to enable efficient, accurate, and scalable query resolution across diverse data formats. By integrating semantic-aware heterogeneous graph indexing and topology-enhanced retrieval with SLM- powered structured data extraction, our system addresses the limitations of traditional methods in handling Multi-Entity Question Answering (Multi-Entity QA) and complex semantic queries. The introduction of semantic entropy as an unsupervised evaluation metric provides robust insights into model uncertainty. Together, these innovations establish a domain-agnostic, resource-efficient paradigm for executing complex queries across structured, semi-structured, and unstructured data sources, aiming at foundational advancement for next-generation intelligent database systems.

This article investigates the problem of exponential bipartite synchronization of fractional-order multilayer signed networks via hybrid impulsive control. First, the mathematical model of the networks is established by integrating the fractional dynamics of nodes, the multilayer network edges, and the positive and negative weights (antagonistic relationship), which is more pluralistic and practical. Second, a hybrid impulsive controller is designed, which is composed of the feedback control part and the impulsive control part to realize the exponential bipartite synchronization objective. Both positive and negative impulsive effects are considered and the ranges of the impulsive control gain related to the order of Caputo fractional derivative are discussed. In addition, some sufficient conditions for exponential bipartite synchronization of fractional-order multilayer signed networks are obtained by using the signed graph theory, Lyapunov method, and average impulsive interval method. Furthermore, in order to illustrate the practicability of the theoretical results, fractional-order coupled Chua's circuits model and fractional-order power systems built on multilayer signed networks are established and the exponential bipartite synchronization issues are analyzed. Numerical examples and simulations are provided to show the effectiveness of the obtained results.