Search Results for author:
Found 39 papers, 18 papers with code
Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs
Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs).
Ranked #2 on
Entity Alignment
on DICEWS-1K
Knowledge Graph Representation Learning using Ordinary Differential Equations
Many KGEs use the Euclidean geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models.
Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models
SoG constructs a context graph by extracting entities and concepts from the original corpus, representing cross-document associations, and employing a graph walk strategy for knowledge-associated sampling.
Financial Wind Tunnel: A Retrieval-Augmented Market Simulator
To address this challenge, we propose Financial Wind Tunnel (FWT), a retrieval-augmented market simulator designed to generate controllable, reasonable, and adaptable market dynamics for model testing.
LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
Despite the growing development of long-context large language models (LLMs), data-centric approaches relying on synthetic data have been hindered by issues related to faithfulness, which limit their effectiveness in enhancing model performance on tasks such as long-context reasoning and question answering (QA).
A Survey on LLM-as-a-Judge
Accurate and consistent evaluation is crucial for decision-making across numerous fields, yet it remains a challenging task due to inherent subjectivity, variability, and scale.
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
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.
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models
As large language models become increasingly prevalent in the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance.
Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning
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.
RuleRAG: Rule-guided retrieval-augmented generation with language models for question answering
To address these issues, we propose Rule-Guided Retrieval-Augmented Generation with LMs, which explicitly introduces symbolic rules as demonstrations for in-context learning (RuleRAG-ICL) to guide retrievers to retrieve logically related documents in the directions of rules and uniformly guide generators to generate answers attributed by the guidance of the same set of rules.
ChartMoE: Mixture of Expert Connector for Advanced Chart Understanding
Combined with the vanilla connector, we initialize different experts in four distinct ways and adopt high-quality knowledge learning to further refine the MoE connector and LLM parameters.
MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in processing and generating content across multiple data modalities.
Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
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.
Financial Knowledge Large Language Model
Secondly, we propose IDEA-FinKER, a Financial Knowledge Enhancement framework designed to facilitate the rapid adaptation of general LLMs to the financial domain, introducing a retrieval-based few-shot learning method for real-time context-level knowledge injection, and a set of high-quality financial knowledge instructions for fine-tuning any general LLM.
Context Graph
Knowledge Graphs (KGs) are foundational structures in many AI applications, representing entities and their interrelations through triples.
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values.
Unlocking the Power of Large Language Models for Entity Alignment
To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy.
A Survey on Large Language Model Hallucination via a Creativity Perspective
Hallucinations in large language models (LLMs) are always seen as limitations.
ChartBench: A Benchmark for Complex Visual Reasoning in Charts
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in image understanding and generation.
On the Evolution of Knowledge Graphs: A Survey and Perspective
Knowledge graphs (KGs) are structured representations of diversified knowledge.
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning.
Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?
The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies.
Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction
In the inductive setting where test TKGs contain emerging entities, the latest methods are based on symbolic rules or pre-trained language models (PLMs).
Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios.
Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph
Different from KGs and TKGs in the transductive setting, constantly emerging entities and relations in incomplete TKGs create demand to predict missing facts with unseen components, which is the extrapolation setting.
Ultrahyperbolic Knowledge Graph Embeddings
Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies.
TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph
In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between).
Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs).
Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations.
Time-aware Relational Graph Attention Network for Temporal Knowledge Graph Embeddings
Embedding-based representation learning approaches for knowledge graphs (KGs) have been mostly designed for static data.
Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings
Representation learning approaches for knowledge graphs have been mostly designed for static data.
Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings
For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same.
Motif Learning in Knowledge Graphs Using Trajectories Of Differential Equations
To this end, we represent each relation (edge) in a KG as a vector field on a smooth Riemannian manifold.
TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferringvarious relation patterns over time.
Knowledge Graph Embeddings in Geometric Algebras
Knowledge graph (KG) embedding aims at embedding entities and relations in a KG into a lowdimensional latent representation space.
Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
Moreover, considering the temporal uncertainty during the evolution of entity/relation representations over time, we map the representations of temporal KGs into the space of multi-dimensional Gaussian distributions.
Toward Understanding The Effect of Loss Function on The Performance of Knowledge Graph Embedding
We show that by a proper selection of the loss function for training the TransE model, the main limitations of the model are mitigated.
Toward Understanding The Effect Of Loss function On Then Performance Of Knowledge Graph Embedding
We show that by a proper selection of the loss function for training the TransE model, the main limitations of the model are mitigated.
LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules
We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph.
Ranked #14 on
Link Prediction
on FB15k
