# Hybrid Graphs for Table-and-Text based Question Answering using LLMs

arXiv: https://arxiv.org/abs/2501.17767 · HTML: https://mlsanity.com/paper/2501.17767/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 29 Jan 2025.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [Open Question Answering over Tables and Text](https://mlsanity.com/paper/2010.10439/) (2020)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [TUTA: Tree-based Transformers for Generally Structured Table Pre-training](https://mlsanity.com/paper/2010.12537/) (2020)
- [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023)
- [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)
- [Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning](https://mlsanity.com/paper/2311.03734/) (2023)
- [Chain-of-Skills: A Configurable Model for Open-domain Question Answering](https://mlsanity.com/paper/2305.03130/) (2023)
- [S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering](https://mlsanity.com/paper/2305.11725/) (2023)
- [Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://mlsanity.com/paper/2210.12338/) (2022)
- [Context-Aware Answer Extraction in Question Answering](https://mlsanity.com/paper/2011.02687/) (2020)

## Built on by (most cited first, 7 of 7)

- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA](https://mlsanity.com/paper/2510.20505/) (2025)
- [AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering](https://mlsanity.com/paper/2503.00435/) (2025)
- [SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables](https://mlsanity.com/paper/2602.23286/) (2026)
- [Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval](https://mlsanity.com/paper/2606.05415/) (2026)
- [Improving Answer Extraction in Context-based Question Answering Systems Using LLMs](https://mlsanity.com/paper/2606.06197/) (2026)
- [TRACE: Trustworthy Retrieval-Augmented Conversational Engine](https://mlsanity.com/paper/2608.10176/) (2026)

## Abstract (arXiv)

Answering questions that require reasoning and aggregation across both structured (tables) and unstructured (raw text) data sources presents significant challenges. Current methods rely on fine-tuning and high-quality, human-curated data, which is difficult to obtain. Recent advances in Large Language Models (LLMs) have shown promising results for multi-hop question answering (QA) over single-source text data in a zero-shot setting, yet exploration into multi-source Table-Text QA remains limited. In this paper, we present a novel Hybrid Graph-based approach for Table-Text QA that leverages LLMs without fine-tuning. Our method constructs a unified Hybrid Graph from textual and tabular data, pruning information based on the input question to provide the LLM with relevant context concisely. We evaluate our approach on the challenging Hybrid-QA and OTT-QA datasets using state-of-the-art LLMs, including GPT-3.5, GPT-4, and LLaMA-3. Our method achieves the best zero-shot performance on both datasets, improving Exact Match scores by up to 10% on Hybrid-QA and 5.4% on OTT-QA. Moreover, our approach reduces token usage by up to 53% compared to the original context.