REVIEW 10 cited by
Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
read the original abstract
Traditional similarity-based schema matching methods are incapable of resolving semantic ambiguities and conflicts in domain-specific complex mapping scenarios due to missing commonsense and domain-specific knowledge. The hallucination problem of large language models (LLMs) also makes it challenging for LLM-based schema matching to address the above issues. Therefore, we propose a Knowledge Graph-based Retrieval-Augmented Generation model for Schema Matching, referred to as the KG-RAG4SM. In particular, KG-RAG4SM introduces novel vector-based, graph traversal-based, and query-based graph retrievals, as well as a hybrid approach and ranking schemes that identify the most relevant subgraphs from external large knowledge graphs (KGs). We showcase that KG-based retrieval-augmented LLMs are capable of generating more accurate results for complex matching cases without any re-training. Our experimental results show that KG-RAG4SM outperforms the LLM-based state-of-the-art (SOTA) methods (e.g., Jellyfish-8B) by 35.89% and 30.50% in terms of precision and F1 score on the MIMIC dataset, respectively; KG-RAG4SM with GPT-4o-mini outperforms the pre-trained language model (PLM)-based SOTA methods (e.g., SMAT) by 69.20% and 21.97% in terms of precision and F1 score on the Synthea dataset, respectively. The results also demonstrate that our approach is more efficient in end-to-end schema matching, and scales to retrieve from large KGs. Our case studies on the dataset from the real-world schema matching scenario exhibit that the hallucination problem of LLMs for schema matching is well mitigated by our solution.
Forward citations
Cited by 10 Pith papers
-
KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval
Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.
-
ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching
ConStruM improves LLM-based schema matching by using a context tree and global similarity hypergraph to assemble query-specific evidence packs from available schema metadata.
-
Graph Construction and Matching for Imperative Programs using Neural and Structural Methods
A pipeline converts programs with annotations into typed attributed graphs using AST parsing and neural embeddings to support verification artefact reuse across languages.
-
Graph Construction and Matching for Imperative Programs using Neural and Structural Methods
A multi-language pipeline converts C/ACSL, Java/JML, and Dafny programs into typed attributed graphs combining AST structure with SentenceTransformer and CodeBERT embeddings.
-
Towards Trustworthy and Cost-Efficient Data Integration: From Na\"ive RAG to Agentic RAG
The paper argues that agentic RAG with adaptive retrieval, iterative reasoning, and graph memory is the path to trustworthy and cost-efficient data integration, and sketches a six-agent architecture.
-
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
SchemaRAG dynamically reduces large schemas via RAG for LLM information extraction, reporting up to 8.8% micro-F1 gain, 47% latency cut, and 48% token cost reduction on healthcare and e-commerce data.
-
Graph Construction and Matching for Imperative Programs using Neural and Structural Methods
A pipeline builds consistent typed attributed graphs from imperative programs and annotations in multiple languages by combining structural parsing with semantic embeddings from code models.
-
Learning-Infused Formal Reasoning: From Contract Synthesis to Artifact Reuse and Formal Semantics
A vision paper proposing Learning-Infused Formal Reasoning (LIFR), a hybrid LLM+graph framework for contract synthesis, artifact reuse, and semantic foundations in verification.
-
LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems
The paper synthesizes three synergies between LLMs and graphs—augmented retrieval/reasoning, bidirectional KG integration, and graph-enhanced agents—plus LLM uses in graph data management and ML.
-
LLM+Graph@VLDB'2025 Workshop Summary
The report summarizes key research directions, challenges, and solutions from the LLM+Graph workshop at VLDB 2025.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.