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

2024-12-02 · Qianlong Li, Chen Huang, Shuai Li, Yuanxin Xiang, Deng Xiong, Wenqiang Lei

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 \url{https://github.com/JDing0521/GraphOTTER}.

📄 PDF Abstract BibTeX arXiv:2412.01230

Code (1)

jding0521/graphotter 공식 구현 pytorch

Tasks

Question Answering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs

2025-12-04 · Hao Wang, Jialun Zhong, Changcheng Wang, Zhujun Nie 외 arxiv

Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suf…

Conversational Question Answering Computational Efficiency Logical Reasoning Knowledge Graphs

CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting

2026-04-20 · Etienne Tajeuna, Patrick Asante Owusu, Armelle Brun, Shengrui Wang arxiv

In this paper we investigate forecasting coevolving time series that feature intricate dependencies and nonstationary dynamics by using an LLM Large Language Models approach We propose a novel modeling approach named Con…

Time Series Forecasting

Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning

2024-05-23 · Jiapu Wang, Kai Sun, Linhao Luo, Wei Wei 외

Temporal Knowledge Graph Reasoning (TKGR) is the process of utilizing temporal information to capture complex relations within a Temporal Knowledge Graph (TKG) to infer new knowledge. Conventional methods in TKGR typical…

EXG: Self-Evolving Agents with Experience Graphs

2026-05-18 · Yuxin Jin, Siyuan Zhang, Hanchen Wang, Lu Qin 외 arxiv

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge …

Code Generation

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

2026-04-20 · Jiahao Huang, Peilan Xu, Xiaoya Nan, Wenjian Luo arxiv

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathemati…