paper-with-me

홈 › Papers

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding

2024-03-28 · Rihui Jin, Yu Li, Guilin Qi, Nan Hu, Yuan-Fang Li, Jiaoyan Chen, Jianan Wang, Yongrui Chen, Dehai Min, Sheng Bi

Table understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures.To address these challenges, we propose HGT, a framework with a heterogeneous graph (HG)-enhanced large language model (LLM) to tackle few-shot TU tasks.It leverages the LLM by aligning the table semantics with the LLM's parametric knowledge through soft prompts and instruction turning and deals with complex tables by a multi-task pre-training scheme involving three novel multi-granularity self-supervised HG pre-training objectives.We empirically demonstrate the effectiveness of HGT, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks.

📄 PDF Abstract BibTeX arXiv:2403.19723

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Heterogeneous Graph Neural Architecture Search with GPT-4

2023-12-14 · Haoyuan Dong, Yang Gao, Haishuai Wang, Hong Yang 외

Heterogeneous graph neural architecture search (HGNAS) represents a powerful tool for automatically designing effective heterogeneous graph neural networks. However, existing HGNAS algorithms suffer from inefficient sear…

Neural Architecture Search

Graph-Driven Models for Gas Mixture Identification and Concentration Estimation on Heterogeneous Sensor Array Signals

2024-12-18 · Ding Wang, Lei Wang, Huilin Yin, Guoqing Gu 외

Accurately identifying gas mixtures and estimating their concentrations are crucial across various industrial applications using gas sensor arrays. However, existing models face challenges in generalizing across heteroge…

ECNU\_ICA\_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning

2021-08-01 · SEMEVAL 2021 · Pingsheng Liu, LinLin Wang, Qian Zhao, Hao Chen 외

This paper describes our system for SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. To accomplish this task, we utilize the Knowledge-Enhanced Graph Attention Network (KEGAT) architecture with a novel sem…

Graph AttentionReading Comprehension

LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network

2020-04-28 · ACL 2020 6 · Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan 외

Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this wo…

Fact CheckingSemantic Parsing

XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model

2024-08-27 · Yasir Ali Farrukh, Syed Wali, Irfan Khan, Nathaniel D. Bastian

In the rapidly evolving field of cybersecurity, the integration of flow-level and packet-level information for real-time intrusion detection remains a largely untapped area of research. This paper introduces "XG-NID," a …

Graph Neural NetworkIntrusion DetectionLanguage ModelingLanguage Modelling+3