Search Results for author: Lei Liang

Found 26 papers, 12 papers with code

UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction

1 code implementation11 Nov 2024 Zhiqiang Liu, Mingyang Chen, Yin Hua, Zhuo Chen, Ziqi Liu, Lei Liang, Huajun Chen, Wen Zhang

Experimental results across 7 datasets from 3 types of KGs demonstrate that our UniHR outperforms baselines designed for one specific kind of KG, indicating strong generalization capability of HiDR form and the effectiveness of HiSL module.

Link Prediction Representation Learning

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

1 code implementation8 Sep 2024 Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang

This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval.

Entity Linking RAG +1

RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment

no code implementations22 Aug 2024 Xiaohan Wang, Xiaoyan Yang, Yuqi Zhu, Yue Shen, Jian Wang, Peng Wei, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks.

Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach

no code implementations18 Jul 2024 Zhouyu Jiang, Mengshu Sun, Lei Liang, Zhiqiang Zhang

Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task.

Multi-hop Question Answering Question Answering +2

Croppable Knowledge Graph Embedding

no code implementations3 Jul 2024 Yushan Zhu, Wen Zhang, Zhiqiang Liu, Mingyang Chen, Lei Liang, Huajun Chen

Knowledge Graph Embedding (KGE) is a common method for Knowledge Graphs (KGs) to serve various artificial intelligence tasks.

Knowledge Graph Embedding Knowledge Graphs +1

TrustUQA: A Trustful Framework for Unified Structured Data Question Answering

no code implementations27 Jun 2024 Wen Zhang, Long Jin, Yushan Zhu, Jiaoyan Chen, Zhiwei Huang, Junjie Wang, Yin Hua, Lei Liang, Huajun Chen

In this paper, we propose UnifiedTQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way.

Answer Generation Knowledge Graphs +2

Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks

1 code implementation21 May 2024 Yichi Zhang, Binbin Hu, Zhuo Chen, Lingbing Guo, Ziqi Liu, Zhiqiang Zhang, Lei Liang, Huajun Chen, Wen Zhang

In response to the lack of open-source benchmarks, we constructed a new multi-domain KGP benchmark called KPI with two large-scale KGs and six different sub-domain tasks to evaluate our method and open-sourced it for subsequent research.

Knowledge Graphs

AntBatchInfer: Elastic Batch Inference in the Kubernetes Cluster

no code implementations15 Apr 2024 Siyuan Li, Youshao Xiao, Fanzhuang Meng, Lin Ju, Lei Liang, Lin Wang, Jun Zhou

Offline batch inference is a common task in the industry for deep learning applications, but it can be challenging to ensure stability and performance when dealing with large amounts of data and complicated inference pipelines.

AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes

no code implementations15 Apr 2024 Youshao Xiao, Lin Ju, Zhenglei Zhou, Siyuan Li, ZhaoXin Huan, Dalong Zhang, Rujie Jiang, Lin Wang, Xiaolu Zhang, Lei Liang, Jun Zhou

Previous works only address part of the stragglers and could not adaptively solve various stragglers in practice.

Prompt-fused framework for Inductive Logical Query Answering

no code implementations19 Mar 2024 Zezhong Xu, Peng Ye, Lei Liang, Huajun Chen, Wen Zhang

Answering logical queries on knowledge graphs (KG) poses a significant challenge for machine reasoning.

Knowledge Graphs

Editing Conceptual Knowledge for Large Language Models

1 code implementation10 Mar 2024 Xiaohan Wang, Shengyu Mao, Ningyu Zhang, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs).

knowledge editing

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

1 code implementation5 Mar 2024 Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Ningyu Zhang, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions.

Hallucination Self-Learning

Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion

1 code implementation22 Feb 2024 Yichi Zhang, Zhuo Chen, Lei Liang, Huajun Chen, Wen Zhang

To address the mentioned problems, we propose Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) to unleash the power of imbalanced modality information for MMKGC.

Multi-modal Knowledge Graph

IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus

1 code implementation22 Feb 2024 Honghao Gui, Lin Yuan, Hongbin Ye, Ningyu Zhang, Mengshu Sun, Lei Liang, Huajun Chen

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE).

Zero-shot Generalization

Unified Hallucination Detection for Multimodal Large Language Models

2 code implementations5 Feb 2024 Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs) are plagued by the critical issue of hallucination.

Hallucination

GLISP: A Scalable GNN Learning System by Exploiting Inherent Structural Properties of Graphs

no code implementations6 Jan 2024 Zhongshu Zhu, Bin Jing, Xiaopei Wan, Zhizhen Liu, Lei Liang, Jun Zhou

As a powerful tool for modeling graph data, Graph Neural Networks (GNNs) have received increasing attention in both academia and industry.

graph partitioning Graph Sampling

An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training

no code implementations19 Dec 2023 Youshao Xiao, Zhenglei Zhou, Fagui Mao, Weichang Wu, Shangchun Zhao, Lin Ju, Lei Liang, Xiaolu Zhang, Jun Zhou

To address these issues, we propose a flexible model placement framework that offers two general and agile model placement strategies.

Rethinking Memory and Communication Cost for Efficient Large Language Model Training

no code implementations9 Oct 2023 Chan Wu, Hanxiao Zhang, Lin Ju, Jinjing Huang, Youshao Xiao, ZhaoXin Huan, Siyuan Li, Fanzhuang Meng, Lei Liang, Xiaolu Zhang, Jun Zhou

In this paper, we rethink the impact of memory consumption and communication costs on the training speed of large language models, and propose a memory-communication balanced strategy set Partial Redundancy Optimizer (PaRO).

Language Modelling Large Language Model

InstructIE: A Bilingual Instruction-based Information Extraction Dataset

3 code implementations19 May 2023 Honghao Gui, Shuofei Qiao, Jintian Zhang, Hongbin Ye, Mengshu Sun, Lei Liang, Jeff Z. Pan, Huajun Chen, Ningyu Zhang

Experimental results demonstrate that large language models trained with InstructIE can not only obtain better IE capabilities but also enhance zero-shot performance compared with baselines.

An Integration and Operation Framework of Geothermal Heat Pumps in Distribution Networks

no code implementations12 Jun 2021 Lei Liang, Xuan Zhang, Hongbin Sun

Besides, in the Virtual Power Plant (VPP) system, the demand response of clustered GHP systems can improve the operating flexibility of the power grid.

energy management Management

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