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

arXiv: https://arxiv.org/abs/2609.13776 · HTML: https://mlsanity.com/paper/2609.13776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark](https://mlsanity.com/paper/2505.18761/) (2025)
- [Magneto: Combining Small and Large Language Models for Schema Matching](https://mlsanity.com/paper/2412.08194/) (2024)
- [ReMatch: Retrieval Enhanced Schema Matching with LLMs](https://mlsanity.com/paper/2403.01567/) (2024)
- [Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL](https://mlsanity.com/paper/2404.12560/) (2024)
- [Exploring the Role of Diversity in Example Selection for In-Context Learning](https://mlsanity.com/paper/2505.01842/) (2025)
- [Matchmaker: Self-Improving Large Language Model Programs for Schema Matching](https://mlsanity.com/paper/2410.24105/) (2024)

## Abstract (arXiv)

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.