# S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering

arXiv: https://arxiv.org/abs/2305.11725 · HTML: https://mlsanity.com/paper/2305.11725/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [Open Question Answering over Tables and Text](https://mlsanity.com/paper/2010.10439/) (2020)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [MATE: Multi-view Attention for Table Transformer Efficiency](https://mlsanity.com/paper/2109.04312/) (2021)
- [Unsupervised Multi-hop Question Answering by Question Generation](https://mlsanity.com/paper/2010.12623/) (2020)
- [Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder](https://mlsanity.com/paper/2209.07692/) (2022)
- [UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation](https://mlsanity.com/paper/2210.08249/) (2022)
- [DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2211.12668/) (2022)
- [Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question](https://mlsanity.com/paper/2305.03458/) (2023)
- [MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering](https://mlsanity.com/paper/2210.10350/) (2022)
- [A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions](https://mlsanity.com/paper/2212.13465/) (2022)

## Built on by (most cited first, 17 of 17)

- [Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?](https://mlsanity.com/paper/2410.23856/) (2024)
- [CABINET: Content Relevance based Noise Reduction for Table Question Answering](https://mlsanity.com/paper/2402.01155/) (2024)
- [ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context](https://mlsanity.com/paper/2403.02177/) (2024)
- [MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2309.04790/) (2023)
- [LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments](https://mlsanity.com/paper/2408.15903/) (2024)
- [FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering](https://mlsanity.com/paper/2404.18585/) (2024)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2310.05157/) (2023)
- [TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering](https://mlsanity.com/paper/2506.03949/) (2025)
- [SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models](https://mlsanity.com/paper/2311.09818/) (2023)
- [SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing](https://mlsanity.com/paper/2406.00562/) (2024)
- [Hybrid Graphs for Table-and-Text based Question Answering using LLMs](https://mlsanity.com/paper/2501.17767/) (2025)
- [TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization](https://mlsanity.com/paper/2406.14732/) (2024)
- [HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering](https://mlsanity.com/paper/2309.12669/) (2023)
- [MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering](https://mlsanity.com/paper/2502.17253/) (2025)
- [Denoising Table-Text Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2403.17611/) (2024)
- [Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes](https://mlsanity.com/paper/2603.14229/) (2026)

## Abstract (arXiv)

Answering multi-hop questions over hybrid factual knowledge from the given text and table (TextTableQA) is a challenging task. Existing models mainly adopt a retriever-reader framework, which have several deficiencies, such as noisy labeling in training retriever, insufficient utilization of heterogeneous information over text and table, and deficient ability for different reasoning operations. In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner. We use a retriever with refinement training to solve the noisy labeling problem. Then, a hybrid selector considers the linked relationships between heterogeneous data to select the most relevant factual knowledge. For the final stage, instead of adapting a reading comprehension module like in previous methods, we employ a generation-based reasoner to obtain answers. This includes two approaches: a row-wise generator and an LLM prompting generator~(first time used in this task). The experimental results demonstrate that our method achieves competitive results in the few-shot setting. When trained on the full dataset, our approach outperforms all baseline methods, ranking first on the HybridQA leaderboard.