Lune

ACL Findings2026

InteracSPARQL : An Interactive System for SPARQL Query Refinement Using Natural Language Explanations

Xiangru Jian, Zhengyuan Dong, M. Tamer Özsu

Abstract

Current approaches for Natural Language to SPARQL (NL2SPARQL) generation primarily rely on one-turn, training-intensive models. While effective in specific settings, these models often lack generalizability and fail to provide transparency or mechanisms for error recovery in realistic scenarios. Additionally, prior interactive works are largely outdated and incompatible with modern large language model (LLM) workflows. In this paper, we introduce INTERACSPARQL, a training-free interactive refinement pipeline that acts as a plug-and-play enhancement for existing SPARQL generation systems. Our approach integrates a set of efficient entity and property lookup tools within a self-correction loop, guided by a novel hybrid Natural Language Explanation (NLE) module. This module combines rule-based Abstract Syntax Tree (AST) parsing with LLM semantic enrichment to produce explanations that are both structurally accurate and linguistically fluent. We evaluate INTERACSPARQL on standard benchmarks (QALD-9 and QALD-10), showing that our tool-augmented self-refinement significantly boosts the accuracy of base models without fine-tuning. Furthermore, human evaluation confirms that our structured explanations substantially improve user understanding and ability to correct queries compared to unstructured baselines. The code and datasets are available at https://github. com/Edward-JianQAQ/InteracSPARQL.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Few-shot In-context Learning on Knowledge Base Question Answering cites DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases
  • StructGPT: A General Framework for Large Language Model to Reason over Structured Data cites UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
  • DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases cites UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic TasksHao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang et al.ICLR 2026 · 6 citations

Builds on8

  1. UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language ModelsTianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong et al.EMNLP 2022 · 222 citations
  2. StructGPT: A General Framework for Large Language Model to Reason over Structured DataJinhao Jiang, Kun Zhou, Zican Dong, Keming Ye et al.EMNLP 2023 · 173 citations
  3. Few-shot In-context Learning on Knowledge Base Question AnsweringTianle Li, Xueguang Ma, Alex Zhuang, Yu Gu et al.ACL 2023 · 55 citations
  4. A Universal Question-Answering Platform for Knowledge GraphsReham Omar, Ishika Dhall, Panos Kalnis, Essam MansourSIGMOD 2023 · 48 citations
  5. DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge BasesDonghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu et al.ICLR 2023 · 18 citations

Related papers

  1. Sphinteract: Resolving Ambiguities in NL2SQL Through User InteractionFuheng Zhao, Shaleen Deep, Fotis Psallidas, Avrilia Floratou et al.VLDB 2025 · 12 citations
  2. DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword ExtractionJian Chen, Zhenyan Chen, Xuming Hu, Peilin Zhou et al.EMNLP Findings 2025 · 1 citation
  3. IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement LearningHaohao Luo, Zexi Li, Yuexiang Xie, Wenhao Zhang et al.ICML 2026
  4. SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQLGeonho Lee, Min-Soo KimVLDB 2026
  5. ReSQL: Self-Improving Framework for Reasoning-Aware Text-to-SQL Dataset GenerationMinjun Park, Yongju Seong, Myoseop Sim, Kyungkoo Min et al.ACL Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines