mlsanityData to 7 Oct 2026

SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing

arXiv 2406.00562 ↗First posted 1 Jun 2024cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge base, text, tables, and infoboxes. Our LLM-augmented approach achieves state-of-the-art performance on the Compmix dataset, the most comprehensive heterogeneous open-domain QA dataset, with 56.5% exact match (EM) rate. More importantly, manual analysis on a sample of the dataset suggests that SPAGHETTI is more than 90% accurate, indicating that EM is no longer suitable for assessing the capabilities of QA systems today.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 1 Jun 2024.

Builds on

26 of 39 references.

References · 26

  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  2. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  3. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  5. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  7. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  8. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  9. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  10. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  11. 2020Open Question Answering over Tables and Textcited by 163
  12. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
14 more
  1. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  2. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  3. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  4. 2020Relevance-guided Supervision for OpenQA with ColBERTcited by 71
  5. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  6. 2024Large Language Model for Table Processing: A Surveycited by 52
  7. 2021Evidentiality-guided Generation for Knowledge-Intensive NLP Taskscited by 40
  8. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  9. 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
  10. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  11. 2021UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Textcited by 17
  12. 2023S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answeringcited by 17
  13. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14
  14. 2023CompMix: A Benchmark for Heterogeneous Question Answeringcited by 12

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 9.

11 papers.

  1. 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
  2. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  3. 2025Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Modelscited by 11
  4. 2024RAG-based Question Answering over Heterogeneous Data and Textcited by 7
  5. 2025Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Modelscited by 4
  6. 2025AutoPK: Leveraging LLMs and a Hybrid Similarity Metric for Advanced Retrieval of Pharmacokinetic Data from Complex Tables and Documentscited by 4
  7. 2025Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Datacited by 3
  8. 2025DBRouting: Routing End User Queries to Databases for Answerabilitycited by 1
  9. 2025Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Datacited by 1
  10. 2025The ReQAP System for Question Answering over Personal Informationcited by 1
  11. 2025SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learningcited by 0