Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs

Siddhesh Thombre; Manasi Patwardhan; Sunita Sarawagi

cs.AISep 12, 2026

Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs

Authors: Siddhesh Thombre, Manasi Patwardhan, Sunita Sarawagi

Organizations: TCS Research · IIT Bombay

Abstract

Integrating heterogeneous relational databases into a centralized ontology remains a persistent challenge in enterprise knowledge representation, primarily due to semantic heterogeneity, cryptic schema naming, missing metadata, and the abstraction gap between relational schemas and ontological models. Although large language models (LLMs) offer strong semantic reasoning capabilities, we show that directly applying them through one-shot prompting or naive multi-stage pipelines leads to poor performance for schema-ontology mapping. This paper presents a self-demonstration-driven approach that combines a neuro-symbolic task decomposition with a novel mechanism for automatically generating pattern-guided, dependency-aware demonstrations to address this integration challenge. Our approach incorporates two key strategies to achieve substantial accuracy gains over existing LLM-based schema integration methods: (i) a neuro-symbolic decomposition of the task into cascaded sub-tasks, where symbolic constraints structure the search space and LLMs perform semantic reasoning within each focused sub-task, and (ii) self-generated demonstrations guided by domain-agnostic patterns to supervise each sub-task. Experiments on three of the most challenging scenarios from the RODI benchmark show that our approach achieves state-of-the-art performance, substantially outperforming (25 percentage points F1 improvements) both traditional schema-to-ontology mapping techniques and recent LLM-based schema-to-ontology and schema matching approaches. Ablation studies further reveal the significant benefits of pattern-guided self-demonstrations and the complementary benefits of neuro-symbolic task decomposition.

Figures & tables

Figure 1: RDB-to-Ontology Mapping Example

Figure 2: Motivation behind Our Approach of DB-to-Ontology Mapping

Figure 3: Overview of Self-Demonstration Driven Mapping Approach. Decomposition: (i) Matching , (ii) Mapping and Self-Demonstrations . $T_{C}$ : Table matched with class $C$ , $C_{S}$ : Subclass of Class $C$ , $D_{C}$ : Data-property of Class $C$ , $T_{K}$ : Table referring to $T_{C}$ , $T_{J}$ : Junction Table

Figure 4: Dependency-Aware context for Self-Demonstrations

Name	Classes	Props.	Tables	Cols.	FKs	Queries
Conference	23	77	66	125	–	39
Mondial	49	71	42	160	60	50
Npd	300	350	70	1000	100	439

Table 1: RODI Scenarios

Traditional Baselines

Scenario	Conf	Mondial	NPD	Avg
AM4O [ 24 ]	0.41	0.44	0.23	0.26
Milan [ 14 ]	0.46	-	0.30	0.31
LLM Driven Baselines
LLM4VKG [ 31 ]	0.51	0.18	0.19	0.21

Table 2: Results on RODI Benchmark with Gemini-2.0-Flash. Conf: Conference-no-fk; NPD: Npd-Atomic; FS: Few-Shot; #: With programmatic mapping;

\dagger

: No Decomposition.

Scenario	Conf	Mondial	Avg
Table-to-KG [ 27 ] #	0.21	0.13	0.17
Magneto [ 13 ] #	0.49	0.34	0.40
Our approach	0.56	0.65	0.61

Table 3: Results on RODI Benchmark with GPT4o. Conf: Conference-no-FK; #: With programmatic mapping.

Semantic Mapping

Semantic mapping links observations and data to meaningful concepts, categories, entities, and relations for machine reasoning and action.

See all 93 papers

Jul 27, 2026

SINT-Flow: Schema Integration using Large Language Model Workflows

The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, attributes, and relationships of all input tables in a coherent fashion. This paper presents SINT-Flow, a schema integration framework composed of five LLM-based operators that can be combined into workflows to perform fully automated, end-to-end schema integration. In contrast to existing approaches, SINT-Flow can process denormalized source tables that contain attributes describing multiple entity types. During the schema integration process, these tables are decomposed into separate entity-specific relations. To evaluate SINT-Flow, we introduce SINT-Bench, a schema integration benchmark comprising 10 schema integration tasks consisting of altogether 93 relational tables, including tables that describe multiple types of entities. We evaluate SINT-Flow using GPT-5.2 as well as the open-weight model Qwen-3.6-27B as alternative backbone models. Using these models, SINT-Flow achieves a Completeness rate of at least 97% in entity type detection, 81% for attribute detection, and an F1-score of 84% for schema mapping. Furthermore, we perform an ablation study to prove the utility of the applied self-consistency strategy as well as the inclusion of a review loop into the Schema Matching Operator.

Keti Korini, Christian Bizer

University of Mannheim Mannheim, Germany

Semantic Mapping Relational Databases Data Integration

Ask PDF

Aug 27, 2026

pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning

Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produce inconsistent formats, and favor hierarchical over associative relations. In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Extension Reuse Task (Task B) using an offline retrieval-augmented few-shot prompting pipeline. Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B. A left-truncated context-windowing strategy preserves task instructions within long prompts. For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's closed term/type vocabulary and removing duplicates of the initial ontology. The approach achieves Semantic Graph Similarity of 0.8692, Term-Typing F1 of 0.9200, and Taxonomy Discovery F1 of 0.8540 on Task B, while Task A achieves 0.7416 Semantic Graph Similarity. However, no non-taxonomic relations are extracted, highlighting limitations of closed, taxonomy-oriented relation vocabularies.

Shivam Mishra, Dhannu Ram Meena, Muneendra Ojha +2

1AIMS Lab, Indian Institute of Information Technology Allahabad, Prayagraj, UP, India

Ontology Learning

Ask PDF

Sep 10, 2026

Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.

Dong-Jae Koh, Huisu Kim, SeongHwan Yoon +4

School of Computer Science and Engineering, Kyungpook National University, South Korea

Multi-Agent LLM Systems LLM Reliability Relational Databases Database Systems

Ask PDF

Abstract

Semantic Mapping

Explore similar work

SINT-Flow: Schema Integration using Large Language Model Workflows

pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning

Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization