HighlightCurated by Aramai EditorialarXiv

CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph

A framework for elevating web-scale corpus construction to structured knowledge organization.

The paper presents Cortex, a three-layer heterogeneous structure (Ontological Corpus Graph) for organizing high-quality corpora. It refines content, evolves ontologies, and enables cross-domain alignment. Comprehensive experiments validate its effectiveness in quality refinement, domain organization, and data synthesis.

Based on: CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph · arXiv

HighlightCurated by Aramai EditorialComputer Science Review

From vectors to knowledge graphs: A comprehensive analysis of modern retrieval-augmented generation architectures

A study on modern retrieval-augmented generation architectures.

The paper analyzes the evolution of retrieval-augmented generation (RAG) models from vector-based representations to knowledge graph-based ones. It provides a comprehensive overview of the current state-of-the-art in RAG architectures and their applications. The authors discuss the benefits and limitations of using knowledge graphs in RAG models.

Based on: From vectors to knowledge graphs: A comprehensive analysis of modern retrieval-augmented generation architectures · Computer Science Review

HighlightCurated by Aramai EditorialarXiv

Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use

A study on the performance of a knowledge-graph tool use recipe with large language models.

The authors test a standard recipe for using knowledge graphs with large language models, observing a 'peak-then-collapse' pattern in performance. They identify four recurring failure modes and argue that interface feedback is a key difference from other tools. The study also explores the effect of self-distillation as a mitigation strategy.

Based on: Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use · arXiv

HighlightCurated by Aramai Editorialopenalex.org

When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation

A framework that calibrates knowledge graph retrieval-augmented generation models.

The paper proposes Ca2KG, a causality-aware calibration framework for KG-RAG. It integrates counterfactual prompting and a panel-based re-scoring mechanism to improve calibration while maintaining predictive accuracy. Experiments on two QA datasets demonstrate the effectiveness of Ca2KG.

Based on: When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation

HighlightCurated by Aramai EditorialarXiv

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

HighlightCurated by Aramai EditorialarXiv

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

HighlightCurated by Aramai EditorialarXiv

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

HighlightCurated by Aramai EditorialarXiv

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

HighlightCurated by Aramai Editorialopenalex.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

HighlightCurated by Aramai EditorialJournal of Industrial Information Integration

Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis

This paper proposes integrating knowledge graphs within a retrieval-augmented generation framework for failure mode and effects analysis data.

The authors propose enhancing retrieval-augmented generation with a knowledge graph to leverage analytical and semantic question-answering capabilities for FMEA data. They present set-theoretic standardization, an algorithm for creating vector embeddings from the FMEA-KG, and a KG-enhanced RAG framework. The approach is validated through a user experience design study.

Based on: Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis · Journal of Industrial Information Integration

HighlightCurated by Aramai EditorialarXiv (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)

HighlightCurated by Aramai EditorialProceedings 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