ACL Findings2024
SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing
Heidi C. Zhang, Sina J. Semnani, Farhad Ghassemi, Jialiang Xu, Shicheng Liu, Monica S. Lam
Abstract
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-ofthe-art performance on the COMPMIX dataset, the most comprehensive heterogeneous opendomain 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. 1
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.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers5
- Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language ModelsQika Lin, Tianzhe Zhao, Kai He, Zhen Peng et al.ACL 2025 · 15 citations
- SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement LearningShicheng Liu, Kai Sun, Lisheng Fu, Xilun Chen et al.ICLR 2026 · 2 citations
- AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge ReasoningAmy Xin, Jinxin Liu, Zijun Yao, Zhicheng Lee et al.KDD 2025 · 1 citation
- Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous DataJiacheng Liu, Mayi Xu, Qiankun Pi, Wenli Li et al.AAAI 2026 · 1 citation
- Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language ModelsSina J. Semnani, Jirayu Burapacheep, Arpandeep Khatua, Thanawan Atchariyachanvanit et al.EMNLP 2025
Builds on13
- DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionMohammadreza Pourreza, Davood RafieiNeurIPS 2023 · 909 citations
- Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question AnsweringAkari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher et al.ICLR 2020 · 322 citations
- Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations
- ReAcTable: Enhancing ReAct for Table Question AnsweringYunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon et al.VLDB 2024 · 120 citations
- Evaluating Open-Domain Question Answering in the Era of Large Language ModelsEhsan Kamalloo, Nouha Dziri, Charles L. A. Clarke, Davood RafieiACL 2023 · 96 citations
Related papers
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual DataWenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong et al.EMNLP Findings 2020 · 205 citations
- Weaver: Interweaving SQL and LLM for Table ReasoningRohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth et al.EMNLP 2025 · 1 citation
- Conversational Question Answering on Heterogeneous SourcesPhilipp Christmann, Rishiraj Saha Roy, Gerhard WeikumSIGIR 2022 · 26 citations
- TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document ReasoningXiaohan Yu, Pu Jian, Chong ChenEMNLP 2025 · 4 citations
- R2-D2: A Modular Baseline for Open-Domain Question AnsweringMartin Fajcik, Martin Docekal, Karel Ondrej, Pavel SmrzEMNLP Findings 2021 · 34 citations
