Search Results for author: Muzhi Li

Found 7 papers, 3 papers with code

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

no code implementations20 Apr 2025 Xinyu Wang, Jijun Chi, Zhenghan Tai, Tung Sum Thomas Kwok, Muzhi Li, Zhuhong Li, Hailin He, Yuchen Hua, Peng Lu, Suyuchen Wang, Yihong Wu, Jerry Huang, Ling Zhou

Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use.

Question Answering RAG +2

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

no code implementations12 Nov 2024 Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King

Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity.

Language Modeling Language Modelling +3

Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning

1 code implementation22 Oct 2024 Muzhi Li, Cehao Yang, Chengjin Xu, Zixing Song, Xuhui Jiang, Jian Guo, Ho-fung Leung, Irwin King

With sufficient guidance from proper prompts and supervised fine-tuning, CATS activates the strong semantic understanding and reasoning capabilities of large language models to assess the existence of query triples, which consist of two modules.

Inductive knowledge graph completion

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

1 code implementation15 Jul 2024 Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, Jian Guo

We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs.

Information Retrieval Knowledge Graphs +6

Context Graph

no code implementations17 Jun 2024 Chengjin Xu, Muzhi Li, Cehao Yang, Xuhui Jiang, Lumingyuan Tang, Yiyan Qi, Jian Guo

Knowledge Graphs (KGs) are foundational structures in many AI applications, representing entities and their interrelations through triples.

Knowledge Graphs Question Answering

The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing

1 code implementation12 Apr 2024 Muzhi Li, Minda Hu, Irwin King, Ho-fung Leung

The Knowledge Graph Entity Typing (KGET) task aims to predict missing type annotations for entities in knowledge graphs.

Entity Typing Knowledge Graphs +1

Momentum Contrastive Pre-training for Question Answering

no code implementations12 Dec 2022 Minda Hu, Muzhi Li, Yasheng Wang, Irwin King

In order to address this problem, we propose a novel Momentum Contrastive pRe-training fOr queStion anSwering (MCROSS) method for extractive QA.

Benchmarking Contrastive Learning +3

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