Knowledge base question answering (KBQA) aims to answer natural language questions using large-scale knowledge bases (KBs). Among various KBQA approaches, semantic parsing-based (SP-based) methods have demonstrated strong effectiveness by generating concise logical forms (LFs) that capture complex subgraph structures and semantic information. Recent research suggests that integrating large language models (LLMs) with SP can achieve significant improvements in the performance and efficiency of KBQA by facilitating the direct generation of LFs with minimal retrieval. However, generating complete LFs with LLMs continues to pose a challenge due to the complexity of the required graph structures and constraints, leading to the significant issue of non-executability. To address these challenges, we propose GCA-KBQA, a step-wise fine-tuned LLM-based framework that employs hop-wise generation, knowledge-assisted calibration, and path-level assembly to construct complete LFs for KBQA. Specifically, we decompose the complex SP process into manageable steps: first, we iteratively generate LFs for each topic entity one hop at a time using a fine-tuned LLM, leveraging KB knowledge to calibrate intermediate outputs and mitigate error propagation. Subsequently, we guide the LLM in assembling path-level LFs from different topic entities, resulting in optimized final LF. We evaluate the proposed method on four KBQA benchmarks spanning two distinct KBs, demonstrating its superior performance compared to state-of-the-art baselines. The code is available at https://github.com/pvfeldt/GCA-KBQA.

Knowledge base question answering (KBQA) refers to the task of answering natural language questions using factual information from large-scale knowledge bases (KBs). To obtain accurate answers, recent research optimizes semantic parsing methods, a major KBQA approach, with large language models (LLMs), where concise logical forms (LFs) are generated by LLMs and executed in KBs. Although these methods demonstrate superior performance, they still encounter the problem that some generated LFs fail to yield answers when executed, significantly limiting their effectiveness. To mitigate this issue, we propose KARV, a Knowledge-Assisted reasoning path Reconstruction and hierarchical Voting approach for non-executable LFs. This method extracts semantic knowledge from KBs as guidance to correct and reconstruct reasoning paths, deriving answers through a voting-based strategy. The insight is that non-executable LFs generated by LLMs still contain rich semantic information, and the knowledge retrieved from KBs can effectively correct them. Specifically, we fine-tune LLMs to generate high-quality LFs, and the nonexecutable LFs are decomposed into multiple path branches based on mentioned entities. Semantic knowledge from KBs is then leveraged to correct the entities and relations within these branches, effectively reconstructing the reasoning paths. To obtain precise final answers, we apply a hierarchical voting strategy both within and across the non-executable LFs. Our proposed method achieves state-of-the-art performance on benchmarks including WebQuestionSP (WebQSP), ComplexWebQuestions (CWQ), and FreebaseQA.

Heterogeneous Information Networks (HINs) are crucial in various intelligent systems. The latest advancements in HIN learning aim to combine meta-paths and hypergraphs, capitalizing on their strengths for further success. However, existing methods typically transform meta-paths into hypergraphs by simply removing the original edges from the meta-paths to integrate two semantics. This will inevitably encounter semantic ambiguity, a so-called semantic-shift problem, during the “meta-path → hyperedges” transforming, causing limited improvements. To address this, we introduce a novel fusion framework that distills knowledge from meta-paths into hypergraphs, mitigating such a problem. Specifically, we propose a unique hyperedge extraction method for constructing the hypergraph, incorporating various aspects instead of relying solely on one type of meta-path. Subsequently, we introduce a shallow student model to capture high-order information from the hypergraph, complementing a teacher model that focuses on encoding low-order information from meta-paths. Then, a distillation framework is employed to integrate explicitly multi-order information into the student. Experimental results across diverse datasets demonstrate a substantial improvement in node classification tasks, with an average accuracy increase of 2.1% over existing state-of-the-art methods.

Management of ship designing is difficult because of the complexity in modeling of the process and large amounts of data throughout the process. Though existing technologies of BPMN can solve the first problem, BPMN does not provide sufficient supports on dealing with complex dependencies in the process, e.g., storage and search problems of correlated data with “many to many” relations. In this paper, we introduce a series of annotations of data objects to solve this problem. First, we extend the annotations of data objects based on BPMN and utilize foreign key in relational database to manage the relations between data objects. Second, we use SQL queries to execute the common operations to data objects in the process. Our approach is the extension of mature BPMN and database technologies, so it is standard and reusable. We implemented our approach on the Produce Management System to verify the availability and efficiency.