Search Results for author: Junnan Dong

Found 13 papers, 2 papers with code

A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

1 code implementation21 Jan 2025 Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, Zheng Yuan, Huachi Zhou, Zijin Hong, Junnan Dong, Hao Chen, Yi Chang, Xiao Huang

Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need for deep expertise.

RAG Retrieval-augmented Generation +1

Benchmarking Large Language Models via Random Variables

no code implementations20 Jan 2025 Zijin Hong, Hao Wu, Su Dong, Junnan Dong, Yilin Xiao, Yujing Zhang, Zhu Wang, Feiran Huang, Linyi Li, Hongxia Yang, Xiao Huang

LLMs must fully understand the problem-solving process for the original problem to correctly answer RV questions with various combinations of variable values.

Benchmarking Mathematical Reasoning

CLR-Bench: Evaluating Large Language Models in College-level Reasoning

no code implementations23 Oct 2024 Junnan Dong, Zijin Hong, Yuanchen Bei, Feiran Huang, Xinrun Wang, Xiao Huang

While emerging benchmarks have been proposed to evaluate LLMs in various domains such as mathematics and computer science, they merely measure the accuracy in terms of the final prediction on multi-choice questions.

Graph Anomaly Detection with Noisy Labels by Reinforcement Learning

no code implementations8 Jul 2024 Zhu Wang, Shuang Zhou, Junnan Dong, Chang Yang, Xiao Huang, Shengjie Zhao

Specifically, we aim to maximize the performance improvement (AUC) of a base detector by cutting noisy edges approximated through the nodes with high-confidence labels.

Fraud Detection Graph Anomaly Detection +2

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL

no code implementations12 Jun 2024 Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, Xiao Huang

Generating accurate SQL from users' natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, database schema comprehension, and SQL generation.

Natural Language Understanding Text to SQL +1

Cost-efficient Knowledge-based Question Answering with Large Language Models

no code implementations27 May 2024 Junnan Dong, Qinggang Zhang, Chuang Zhou, Hao Chen, Daochen Zha, Xiao Huang

We are motivated to combine LLMs and prior small models on knowledge graphs (KGMs) for both inferential accuracy and cost saving.

Knowledge Graphs Model Selection +2

Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering

no code implementations20 Feb 2024 Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, Xiao Huang

Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a scene graph with detailed visual features; (ii) We construct a coupled concept graph by linking the mentioned entities with external facts.

Knowledge Graphs Question Answering +1

Structure Guided Large Language Model for SQL Generation

no code implementations19 Feb 2024 Qinggang Zhang, Hao Chen, Junnan Dong, Shengyuan Chen, Feiran Huang, Xiao Huang

Recent advancements in large language models (LLMs) have shown promise in bridging the gap between natural language queries and database management systems, enabling users to interact with databases without the background of SQL.

Language Modeling Language Modelling +5

KnowGPT: Knowledge Graph based Prompting for Large Language Models

no code implementations11 Dec 2023 Qinggang Zhang, Junnan Dong, Hao Chen, Daochen Zha, Zailiang Yu, Xiao Huang

However, most state-of-the-art LLMs are closed-source, making it challenging to develop a prompting framework that can efficiently and effectively integrate KGs into LLMs with hard prompts only.

Knowledge Graphs Prompt Engineering +2

Contrastive Knowledge Graph Error Detection

1 code implementation18 Nov 2022 Qinggang Zhang, Junnan Dong, Keyu Duan, Xiao Huang, Yezi Liu, Linchuan Xu

To this end, we propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED).

Contrastive Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.