# FRASE: Structured Representations for Generalizable SPARQL Query Generation

arXiv: https://arxiv.org/abs/2503.22144 · HTML: https://mlsanity.com/paper/2503.22144/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [Making Text Embedders Few-Shot Learners](https://mlsanity.com/paper/2409.15700/) (2024)
- [ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models](https://mlsanity.com/paper/2310.08975/) (2023)
- [The language of prompting: What linguistic properties make a prompt successful?](https://mlsanity.com/paper/2311.01967/) (2023)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs](https://mlsanity.com/paper/2410.06062/) (2024)
- [Open-Domain Frame Semantic Parsing Using Transformers](https://mlsanity.com/paper/2010.10998/) (2020)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [Entity Retrieval for Answering Entity-Centric Questions](https://mlsanity.com/paper/2408.02795/) (2024)
- [A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questions](https://mlsanity.com/paper/2304.07772/) (2023)
- [Coarse-to-Fine Dual Encoders are Better Frame Identification Learners](https://mlsanity.com/paper/2310.13316/) (2023)
- [Open-source Frame Semantic Parsing](https://mlsanity.com/paper/2303.12788/) (2023)
- [Can LLMs Extract Frame-Semantic Arguments?](https://mlsanity.com/paper/2502.12516/) (2025)
- [Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval](https://mlsanity.com/paper/2502.13369/) (2025)
- [Enhancing Frame Detection with Retrieval Augmented Generation](https://mlsanity.com/paper/2502.12210/) (2025)

## Built on by (most cited first, 2 of 2)

- [DeSQ: Decomposition-based SPARQL Query Generation](https://mlsanity.com/paper/2606.00203/) (2026)
- [KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation](https://mlsanity.com/paper/2609.01780/) (2026)

## Abstract (arXiv)

Translating natural language questions into SPARQL queries enables Knowledge Base querying for factual and up-to-date responses. However, existing datasets for this task are predominantly template-based, leading models to learn superficial mappings between question and query templates rather than developing true generalization capabilities. As a result, models struggle when encountering naturally phrased, template-free questions. This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to address this limitation. We also present LC-QuAD 3.0, a new dataset derived from LC-QuAD 2.0, in which each question is enriched using FRASE through frame detection and the mapping of frame-elements to their argument. We evaluate the impact of this approach through extensive experiments on recent large language models (LLMs) under different fine-tuning configurations. Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance, particularly in challenging generalization scenarios when test questions feature unseen templates (unknown template splits) and when they are all naturally phrased (reformulated questions).