HighlightarXiv

Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation

Paper on optimizing information demand coverage in retrieval-augmented generation.

This paper proposes a method to optimize information demand coverage in retrieval-augmented generation (RAG) models. The approach aims to improve the ability of RAG models to retrieve relevant information from external sources. The authors evaluate their method on several benchmarks and demonstrate its effectiveness in improving the performance of RAG models.

Based on: Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation · arXiv

HighlightarXiv

Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models

A research paper exploring generalization in knowledge graph foundation models.

The authors investigate the ability of knowledge graph foundation models to generalize from partial links. They examine whether providing half a link is sufficient for accurate predictions. The study aims to understand how these models can be improved for more efficient and effective knowledge retrieval.

Based on: Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models · arXiv

HighlightarXiv

RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

Paper proposing a method for multi-hop knowledge graph question answering using recurrent soft-flow and decoupled large language model generation.

The paper introduces RSF-GLLM, a framework that addresses the semantic gap in multi-hop knowledge graph question answering. It combines recurrent soft-flow with decoupled large language model generation to improve performance. The method is evaluated on several benchmarks and shows promising results.

Based on: RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation · arXiv

HighlightarXiv

Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain

A paper discussing limitations of retrieval-augmented generation in the legal domain.

The authors examine structural, temporal, and causal limitations of retrieval-augmented generation (RAG) in the legal domain. They argue that RAG models have inherent biases and limitations when dealing with complex legal concepts and relationships. The paper highlights the need for more robust and accurate methods to handle legal knowledge graphs.

Based on: Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain · arXiv

HighlightarXiv

Static Analysis of Recursive SHACL

Paper on static analysis of recursive SHACL.

The paper presents a static analysis approach for recursive SHACL shapes. It aims to improve the validation and optimization of SHACL-based data validation rules. The authors propose a novel algorithm for analyzing recursive SHACL shapes, enabling more efficient and effective data validation.

Based on: Static Analysis of Recursive SHACL · arXiv

Highlightopenalex.org

Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation

Paper on using knowledge graphs to improve recommendation systems with large language models.

This paper presents a method called Knowledge Graph Retrieval-Augmented Generation (KG-RAG) that combines knowledge graph retrieval and augmented generation techniques to enhance the performance of large language model-based recommendation systems. The authors propose a framework that leverages knowledge graphs to retrieve relevant information and then uses this information to augment the input of the large language model. Experimental results demonstrate the effectiveness of KG-RAG in improving the accuracy and diversity of recommendations.

Based on: Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation

HighlightarXiv (Cornell University)

Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation

A training-free strategy to enhance structure information in knowledge graph retrieval-augmented generation methods.

The authors propose path pooling, a simple and plug-and-play method that introduces structure information through a novel path-centric pooling operation. This approach seamlessly integrates into existing KG-RAG methods, enabling richer structure information utilization. Extensive experiments demonstrate improved performance with negligible additional cost.

Based on: Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation · arXiv (Cornell University)

HighlightProceedings of the AAAI Conference on Artificial Intelligence

A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation

This paper explores the alignment of knowledge graphs with large language models in retrieval augmented generation.

The authors investigate the factors affecting knowledge graph alignment with large language models, including graph transformation and linearization phases. They conduct experiments on 15 typical LLMs and three common datasets to identify optimal factors for improvement. The study finds that centrality of the KG, formats, orders, and templates significantly impact KGA.

Based on: A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation · Proceedings of the AAAI Conference on Artificial Intelligence

Highlightopenalex.org

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation

A novel RAG framework that augments retrieval with logical reasoning through graph-structured knowledge exploration.

The paper proposes HopRAG, a framework that constructs a passage graph and employs a retriever-reason-prune mechanism to identify relevant passages based on logical connections. Experiments demonstrate improved final answer quality on multi-hop benchmarks. The framework expands the retrieval scope by exploring multi-hop neighbors guided by pseudo-queries and LLM reasoning.

Based on: HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation

Highlightopenalex.org

MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot

A retrieval-augmented generation model enhanced by knowledge graph-elicited reasoning for healthcare copilots.

This paper proposes MedRAG, a RAG model that integrates knowledge graphs and large language models to improve diagnostic accuracy in healthcare. It constructs a hierarchical diagnostic KG and retrieves EHRs to provide more accurate decision support. Experimental results show that MedRAG outperforms state-of-the-art models in reducing misdiagnosis rates.

Based on: MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot

HighlightApplied Intelligence

Knowledge graph-extended retrieval augmented generation for question answering

A paper proposing a system that integrates Large Language Models and Knowledge Graphs for robust question answering.

The paper presents a system, called KG-RAG, which combines Large Language Models and Knowledge Graphs to improve question answering. It includes a question decomposition module and uses In-Context Learning and Chain-of-Thought prompting to generate explicit reasoning chains. Experiments show improved accuracy for multi-hop questions compared to baselines.

Based on: Knowledge graph-extended retrieval augmented generation for question answering · Applied Intelligence

Highlightopenalex.org

Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph

A paper proposing an approach to personalize large language models using retrieval augmented generation with knowledge graphs.

The authors propose a method to address over-fitting in large language models by incorporating knowledge graphs for personalized response generation. They use calendar data as an example of frequently updated personal information. Experimental results show improved accuracy and response time compared to baseline LLMs.

Based on: Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph