GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation

• URL: http://arxiv.org/abs/2607.28082v1
• Date: Thu, 30 Jul 2026 11:52:09 GMT
• Title: GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
• Abstract summary: Generator-Gate-Corrector (GGC) is a framework for reliable Text-to-SPARQL generation.<n>GGC first uses a Generator to produce an initial query, then applies a Gate to predict whether correction is needed, and finally invokes a Corrector only for high-risk queries.<n>Experiments show that GGC improves query-level accuracy from 90.23% to 98.33% while reducing inference overhead by 45%.
• Score: 21.730811527808907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated strong capabilities in structured query generation, making them a natural choice for Text-to-SPARQL, which translates natural language questions into executable SPARQL queries over knowledge graphs. However, their initial outputs remain unreliable: generated queries may be executable yet semantically misaligned with input questions, leading to incorrect retrieval. To address this issue, we propose Generator-Gate-Corrector (GGC), a framework for reliable LLM-based Text-to-SPARQL generation. GGC first uses a Generator to produce an initial query, then applies a Gate to predict whether correction is needed, and finally invokes a Corrector only for selected high-risk queries. This selective correction mechanism avoids unnecessary modifications and reduces the risk of degrading originally correct queries. Experiments on MCQA show that GGC improves query-level accuracy from 90.23\% to 98.33\% while reducing inference overhead by 45\% compared with correcting all generated queries. Ablation studies show that the Gate is robust across thresholds and that Corrector training data composition affects correction effectiveness and stability. Overall, the results demonstrate that selective correction enhances the accuracy, reliability, and efficiency of LLM-based text-to-SPARQL generation.

Related papers

• Towards Researcher Agents for Knowledge-Graph Question Answering [0.0]
  We present an agentic text-to-SPARQL system that goes one step beyond static tool-using agents.<n>We instantiate the loop on DBpedia, evolve nine successive versions of the agent driven by a low-cost reasoning model, and deploy the best-performing configuration.
  arXiv  Detail & Related papers  (2026-08-07T18:42:53Z)
• Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines [48.34524144147475]
  Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines.<n>We investigate Query Performance Prediction (QPP) as a mechanism for variant selection across ad-hoc retrieval and end-to-end RAG.
  arXiv  Detail & Related papers  (2026-04-24T15:36:40Z)
• Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL [1.5773713958458309]
  No open, execution-based benchmark exists for mapping natural language to Jira Query Language (JQL)<n>We introduce Jackal, the first large-scale, execution-based text-to-JQL benchmark comprising 100,000 validated NL-JQL pairs on a live Jira instance with over 200,000 issues.
  arXiv  Detail & Related papers  (2026-04-10T16:27:31Z)
• FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs [0.5120567378386615]
  We propose a modular framework that supports fine-tuned LLMs as a core component, with optional context provided via RAG and a SPARQL query correction layer.<n>We measure query accuracy using BLEU and ROUGE metrics, and query result accuracy using relaxed exact match(RelaxedEM)<n> Experimental results demonstrate that fine-tuning achieves the highest overall performance, reaching 0.90 ROUGE-L for query accuracy and 0.85 RelaxedEM for result accuracy on the test set.
  arXiv  Detail & Related papers  (2025-08-14T09:08:50Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors [23.225358970952197]
  Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs)<n>QE-RAG is the first robust RAG benchmark designed specifically to evaluate performance against query entry errors.<n>We propose a contrastive learning-based robust retriever training method and a retrieval-augmented query correction method.
  arXiv  Detail & Related papers  (2025-04-05T05:24:08Z)
• Tgea: An error-annotated dataset and benchmark tasks for text generation from pretrained language models [57.758735361535486]
  TGEA is an error-annotated dataset for text generation from pretrained language models (PLMs)<n>We create an error taxonomy to cover 24 types of errors occurring in PLM-generated sentences.<n>This is the first dataset with comprehensive annotations for PLM-generated texts.
  arXiv  Detail & Related papers  (2025-03-06T09:14:02Z)
• Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs [51.33342412699939]
  Knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. Recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. We propose an effective Query Instruction Parsing (QIPP) that captures latent query patterns from code-like query instructions.
  arXiv  Detail & Related papers  (2024-10-27T03:18:52Z)
• DAC: Decomposed Automation Correction for Text-to-SQL [51.48239006107272]
  We introduce De Automation Correction (DAC), which corrects text-to-composed by decomposing entity linking and skeleton parsing. We show that our method improves performance by $3.7%$ on average of Spider, Bird, and KaggleDBQA compared with the baseline method.
  arXiv  Detail & Related papers  (2024-08-16T14:43:15Z)
• Optimizing Query Generation for Enhanced Document Retrieval in RAG [53.10369742545479]
  Large Language Models (LLMs) excel in various language tasks but they often generate incorrect information. Retrieval-Augmented Generation (RAG) aims to mitigate this by using document retrieval for accurate responses.
  arXiv  Detail & Related papers  (2024-07-17T05:50:32Z)
• Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue! [1.0786522863027366]
  We present an approach that consists of 1) Ontology-based Query Check (OBQC) and 2) LLM Repair. Our approach increases the overall accuracy to 72% including an additional 8% of "I don't know" unknown results.
  arXiv  Detail & Related papers  (2024-05-20T00:28:00Z)
• Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering [48.43453390717167]
  We present and tackle the problem of Embodied Question Answering with Situational Queries (S-EQA) in a household environment.<n>Unlike prior EQA work, situational queries require the agent to correctly identify multiple object-states and reach a consensus on their states for an answer.<n>We introduce a novel Prompt-Generate-Evaluate scheme that wraps around an LLM's output to generate unique situational queries and corresponding consensus object information.
  arXiv  Detail & Related papers  (2024-05-08T00:45:20Z)
• Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction [50.66922361766939]
  It is crucial to ensure the user's comprehension of a reason for correction. Existing studies present tokens, examples, and hints as to the basis for correction but do not directly explain the reasons for corrections. Generating explanations for GEC corrections involves aligning input and output tokens, identifying correction points, and presenting corresponding explanations consistently. This study introduces a method called controlled generation with Prompt Insertion (PI) so that LLMs can explain the reasons for corrections in natural language.
  arXiv  Detail & Related papers  (2023-09-20T16:14:10Z)
• A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questions [2.5782420501870296]
  In recent years, the field of neural machine translation (NMT) for SPARQL query generation has witnessed significant growth. This paper presents various experiments that replicate and expand upon recent NMT-based SPARQL generation studies.
  arXiv  Detail & Related papers  (2023-04-16T13:12:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.