TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
Not on the map. Why?
Abstract (arXiv)
Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions include question to formal query parsing and retrieval-based answer generation. However, current methods of the former often suffer from weak generalization, failing to dealing with multi-types of sources, while the later is limited in trustfulness. In this paper, we propose TrustUQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way. To this end, it adopts an LLM-friendly and unified knowledge representation method called Condition Graph(CG), and uses an LLM and demonstration-based two-level method for CG querying. For enhancement, it is also equipped with dynamic demonstration retrieval. We have evaluated TrustUQA with 5 benchmarks covering 3 types of structured data. It outperforms 2 existing unified structured data QA methods. In comparison with the baselines that are specific to one data type, it achieves state-of-the-art on 2 of the datasets. Further more, we have demonstrated the potential of our method for more general QA tasks, QA over mixed structured data and QA across structured data. The code is available at https://github.com/zjukg/TrustUQA.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 37 of its 70 references that are in the map. First posted on arXiv 27 Jun 2024.
Builds on
37 of 70 references.
References · 37
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
- 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
- 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
- 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
- 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
25 more
- 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
- 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
- 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
- 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
- 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
- 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
- 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
- 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
- 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graphcited by 100
- 2021Question Answering Over Temporal Knowledge Graphscited by 99
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
- 2018Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsingcited by 57
- 2023TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPTcited by 57
- 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
- 2018FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systemscited by 50
- 2023Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answeringcited by 27
- 2024Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environmentscited by 27
- 2021TempoQR: Temporal Question Reasoning over Knowledge Graphscited by 26
- 2022Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphscited by 26
- 2023Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generationcited by 24
- 2023ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graphcited by 23
- 2023An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answeringcited by 19
- 2023A Universal Question-Answering Platform for Knowledge Graphscited by 17
Built on by
Citing papers per year: 2024: 1; 2025: 6; 2026: 5.
12 papers.
- 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarkingcited by 11
- 2025FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modescited by 6
- 2024Reasoning Factual Knowledge in Structured Data with Large Language Modelscited by 3
- 2025Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledgecited by 3
- 2025Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answeringcited by 2
- 2025Self-Correction Distillation for Structured Data Question Answeringcited by 2
- 2025Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoningcited by 1
- 2026CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoningcited by 0
- 2026Improving Answer Extraction in Context-based Question Answering Systems Using LLMscited by 0
- 2026SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillationcited by 0
- 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answeringcited by 0
- 2026DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extractioncited by 0
- 2026DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction22 Aug 2026
- 2026SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation9 Jul 2026
- 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering20 Jun 2026
- 2026Improving Answer Extraction in Context-based Question Answering Systems Using LLMs4 Jun 2026
- 2026CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning1 Jun 2026
- 2025Self-Correction Distillation for Structured Data Question Answering11 Nov 2025
- 2025Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning25 Aug 2025
- 2025Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering12 Aug 2025
- 2025FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes3 Jun 2025
- 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking29 May 2025
- 2025Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge17 Apr 2025
- 2024Reasoning Factual Knowledge in Structured Data with Large Language Models22 Aug 2024