# SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding

arXiv: https://arxiv.org/abs/2407.01626 · HTML: https://mlsanity.com/paper/2407.01626/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 29 Jun 2024.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2210.00063/) (2022)
- [Efficient One-Pass End-to-End Entity Linking for Questions](https://mlsanity.com/paper/2010.02413/) (2020)
- [Few-shot In-context Learning for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.01750/) (2023)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering](https://mlsanity.com/paper/2308.12060/) (2023)
- [ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering](https://mlsanity.com/paper/2204.08109/) (2022)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [Neural Machine Translating from Natural Language to SPARQL](https://mlsanity.com/paper/1906.09302/) (2019)
- [Falcon 2.0: An Entity and Relation Linking Tool over Wikidata](https://mlsanity.com/paper/1912.11270/) (2019)
- [FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering](https://mlsanity.com/paper/2306.14722/) (2023)
- [A Universal Question-Answering Platform for Knowledge Graphs](https://mlsanity.com/paper/2303.00595/) (2023)
- [Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base](https://mlsanity.com/paper/2109.03614/) (2021)
- [Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs](https://mlsanity.com/paper/2111.00732/) (2021)
- [A Two-Stage Approach towards Generalization in Knowledge Base Question Answering](https://mlsanity.com/paper/2111.05825/) (2021)
- [Question Decomposition Tree for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2306.07597/) (2023)

## Built on by (most cited first, 5 of 5)

- [CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era](https://mlsanity.com/paper/2412.18702/) (2024)
- [Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning](https://mlsanity.com/paper/2509.26383/) (2025)
- [InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanations](https://mlsanity.com/paper/2511.02002/) (2025)
- [CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right](https://mlsanity.com/paper/2506.13070/) (2025)
- [Towards Researcher Agents for Knowledge-Graph Question Answering](https://mlsanity.com/paper/2608.07700/) (2026)

## Abstract (arXiv)

Existing KBQA methods have traditionally relied on multi-stage methodologies, involving tasks such as entity linking, subgraph retrieval and query structure generation. However, multi-stage approaches are dependent on the accuracy of preceding steps, leading to cascading errors and increased inference time. Although a few studies have explored the use of end-to-end models, they often suffer from lower accuracy and generate inoperative query that is not supported by the underlying data. Furthermore, most prior approaches are limited to the static training data, potentially overlooking the evolving nature of knowledge bases over time. To address these challenges, we present a novel end-to-end natural language to SPARQL framework, SPARKLE. Notably SPARKLE leverages the structure of knowledge base directly during the decoding, effectively integrating knowledge into the query generation. Our study reveals that simply referencing knowledge base during inference significantly reduces the occurrence of inexecutable query generations. SPARKLE achieves new state-of-the-art results on SimpleQuestions-Wiki and highest F1 score on LCQuAD 1.0 (among models not using gold entities), while getting slightly lower result on the WebQSP dataset. Finally, we demonstrate SPARKLE's fast inference speed and its ability to adapt when the knowledge base differs between the training and inference stages.