# GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering

arXiv: https://arxiv.org/abs/2412.01230 · HTML: https://mlsanity.com/paper/2412.01230/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [A Survey of Large Language Models for Graphs](https://mlsanity.com/paper/2405.08011/) (2024)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)
- [AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry](https://mlsanity.com/paper/2106.12944/) (2021)
- [SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)](https://mlsanity.com/paper/2105.13995/) (2021)
- [Large Language Models are Complex Table Parsers](https://mlsanity.com/paper/2312.11521/) (2023)
- [A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications](https://mlsanity.com/paper/2404.14809/) (2024)
- [Can LLMs perform structured graph reasoning?](https://mlsanity.com/paper/2402.01805/) (2024)

## Built on by (most cited first, 18 of 18)

- [CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning](https://mlsanity.com/paper/2512.17312/) (2025)
- [Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering](https://mlsanity.com/paper/2412.20145/) (2024)
- [RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis](https://mlsanity.com/paper/2506.13405/) (2025)
- [RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals](https://mlsanity.com/paper/2505.15110/) (2025)
- [ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG](https://mlsanity.com/paper/2510.13193/) (2025)
- [EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks](https://mlsanity.com/paper/2511.08206/) (2025)
- [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)
- [AutoPK: Leveraging LLMs and a Hybrid Similarity Metric for Advanced Retrieval of Pharmacokinetic Data from Complex Tables and Documents](https://mlsanity.com/paper/2510.00039/) (2025)
- [Synergizing LLMs and Knowledge Graphs: A Novel Approach to Software Repository-Related Question Answering](https://mlsanity.com/paper/2412.03815/) (2024)
- [Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization](https://mlsanity.com/paper/2507.22829/) (2025)
- [Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models](https://mlsanity.com/paper/2602.01969/) (2026)
- [Matching Game Preferences Through Dialogical Large Language Models: A Perspective](https://mlsanity.com/paper/2507.20000/) (2025)
- [MissionHD: Hyperdimensional Refinement of Distribution-Deficient Reasoning Graphs for Video Anomaly Detection](https://mlsanity.com/paper/2508.14746/) (2025)
- [QUIETT: Query-Independent Table Transformation for Robust Reasoning](https://mlsanity.com/paper/2602.20017/) (2026)
- [DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering](https://mlsanity.com/paper/2603.09152/) (2026)
- [A Multi-Agent Approach for Claim Verification from Tabular Data Documents](https://mlsanity.com/paper/2604.17225/) (2026)
- [Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search](https://mlsanity.com/paper/2609.00618/) (2026)
- [Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation](https://mlsanity.com/paper/2609.10923/) (2026)

## Abstract (arXiv)

Complex Table Question Answering involves providing accurate answers to specific questions based on intricate tables that exhibit complex layouts and flexible header locations. Despite considerable progress having been made in the LLM era, the reasoning processes of existing methods are often implicit, feeding the entire table into prompts, making it difficult to effectively filter out irrelevant information in the table. To this end, we propose GraphOTTER that explicitly establishes the reasoning process to pinpoint the correct answers. In particular, GraphOTTER leverages a graph-based representation, transforming the complex table into an undirected graph. It then conducts step-by-step reasoning on the graph, with each step guided by a set of pre-defined intermediate reasoning actions. As such, it constructs a clear reasoning path and effectively identifies the answer to a given question. Comprehensive experiments on two benchmark datasets and two LLM backbones demonstrate the effectiveness of GraphOTTER. Further analysis indicates that its success may be attributed to the ability to efficiently filter out irrelevant information, thereby focusing the reasoning process on the most pertinent data. Our code and experimental datasets are available at urlhttps://github.com/JDing0521/GraphOTTER.