Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 4659-4670· 0 citations· 23 references
Abstract
Relational databases (RDBs) play an essential role in real-world scenarios, such as e-commerce, social media, and industry. Recently, with the rapid development of Large Language Models (LLMs), using LLMs to exploit RDBs has become a significant trend. Plenty of works have been proposed to use natural language to describe RDBs or use graph neural networks~(GNNs) to embed relations in RDBs before applying LLMs to them. Despite the achieved progress, existing works still suffer from inevitable weaknesses. For one thing, using natural language to describe RDBs not only causes excessive context length, but also leads to the loss of critical structural information. For another, using GNNs to capture complex structural dependencies requires extensive human-labeled data for supervised fine-tuning, limiting their scalability. Therefore, one important question remains unsolved: '' How to leverage the capability of LLMs to realize robust relational reasoning in RDBs? '' In response, we propose a novel self-supervised framework (ZeroRel) for relational reasoning over RDBs. ZeroRel treats context sparsity as a controllable curriculum variable and leverages it to induce a progressive shift from semantic-dominant inference to structure-aware relational reasoning. Specifically, ZeroRel contains two key modules: Graph-guided Prompt Alignment (GrPA) and Progressive Sparsity-based Context Refinement (PSCR). GrPA uses a heterogeneous GNN to encode multi-table relational structures and projects the resulting structural embeddings into the semantic space of LLMs. PSCR gradually reduces visible attribute context and acts as an information bottleneck, forcing the model to internalize cross-table dependencies rather than relying on superficial semantic shortcuts. Finally, extensive experiments over 7 datasets and 12 downstream tasks demonstrate the superiority of ZeroRel. Furthermore, ZeroRel trained without any task-specific labels achieves an average improvement of 6.24% over models trained with supervised labels.
While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explores whether NLI can be performed using only interpretable, graph-based representations of evidence. We introduce a fully graph-based pipeline where the classifier never directly processes the input text. Instead, sentences are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and represented as three graphs per pair: premise, hypothesis, and a retrieved ConceptNet subgraph. These graphs are then fed into a fine-tuned 0.8-billion-parameter language model. On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model. On ANLI, it matches the published performance of RoBERTa-large on rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) but trails by 16 points on R1, resulting in an overall gap of 9 to 14 points compared to its text counterpart. We term this gap the price of interpretability and demonstrate that it stems from representational limitations rather than data constraints. Ablation studies further reveal that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.
Younes Boufouss, Luc Pommeret, Thomas Gerald et al.· 0 citations
This survey examines how these methods integrate graphs into various stages of the LLM pipeline, including the input, model, and output phases, and outlines the challenges and future research directions for developing more efficient and interpretable solutions.
Xin-Yan Zhu, Cheng Yang, Qiu-Yue Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
To bridge the semantic gap in NL2SQL (Natural Language to SQL) tasks, this study proposes a "Question→SQL→Wiki" framework that leverages a dynamic Wiki Graph as an intermediate reasoning layer. Departing from conventional NL2SQL approaches that rely solely on end-to-end mapping, our method utilizes Large Language Models (LLMs) to translate natural language questions into SQL queries, subsequently parsing these queries to construct a context-specific Wiki Graph. Unlike static knowledge graphs, this architecture emulates the associative and incremental nature of encyclopedic systems, explicitly modeling both database schemas and query-specific logic. By transforming abstract linguistic intent into a structured, wiki-style representation prior to execution, the framework significantly enhances schema linking and logical correctness. Experiments demonstrate that this graph-augmented paradigm improves the accuracy and robustness of NL2SQL systems, offering a scalable solution for complex query generation over relational databases.
Jia-Xuan Liu, Shi-Yu Fang, Jibing Wu et al.· 2026 12th International Conf...· 0 citations
This work presents the first systematic study of inverse relation directionality in LLMs, using a benchmark consisting of 5,457 instances spanning 27 distinct inverse relation labels and reveals systematic asymmetries in inverse relation classification across LLMs.
This work proposes H2Table (Hierarchical Hypergraph-Enhanced Table Reasoning), a novel framework that represents complex tables as hierarchical nested hypergraphs, and designs a tailored hypergraph encoder to facilitate message passing between hyperedges and nodes within complex tables.
Jia Ling, Yang-Fan Wang, Chen Tang et al.· 0 citations
AssistEM, a framework for efficient LLM adaptation to EM via principled data selection, demonstrates that selective fine-tuning not only accelerates adaptation but also improves training efficiency (requiring fewer GPU hours), enabling open-source LLMs to rival–and in some cases outperform–closed-source models.
John Bosco Mugeni, Steven J. Lynden, Toshiyuki Amagasa et al.· International Journal of Dat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
