HighlightCurated by Aramai Editorial

BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration

A paper proposing a method for bootstrapping e-commerce attribute taxonomies using human-AI collaboration.

The authors present BEATS, an approach to iteratively refine e-commerce attribute taxonomies through human-AI collaboration. This method aims to improve search performance by leveraging AI-driven suggestions and human feedback. The proposed framework is designed to be applicable in various e-commerce scenarios.

Based on: BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration · arXiv

HighlightCurated by Aramai Editorial

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 Editorial

VADAOrchestra: Neurosymbolic Orchestration of Adaptive Reasoning Workflows

A paper proposing a neurosymbolic orchestration framework for adaptive reasoning workflows.

The authors present VADAOrchestra, a framework that combines neural networks and symbolic reasoning to adaptively reason over complex tasks. This approach enables the efficient execution of multiple tasks with varying levels of complexity. The framework is designed to be modular and scalable, allowing it to handle diverse task requirements.

Based on: VADAOrchestra: Neurosymbolic Orchestration of Adaptive Reasoning Workflows · arXiv

HighlightCurated by Aramai Editorial

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

HighlightCurated by Aramai Editorial

Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

Paper proposing a method for learning to reason by analogy using retrieval-augmented reinforcement fine-tuning.

The paper presents a novel approach to analogical reasoning, combining retrieval-augmented models with reinforcement learning. The proposed method is evaluated on various tasks and demonstrates improved performance compared to existing methods. This work contributes to the development of more efficient and effective analogical reasoning systems.

Based on: Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning · arXiv

HighlightCurated by Aramai Editorial

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 Editorial

Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization

A generative AI system integrating Retrieval-Augmented Generation, Vector Stores, and Knowledge Graphs for legal information retrieval.

The paper presents a jurisdiction-specific legal information retrieval system that combines Retrieval-Augmented Generation, Vector Stores, and Knowledge Graphs constructed via Hierarchical Non-Negative Matrix Factorization. The system is designed to enhance information retrieval and AI reasoning in the legal domain, minimizing hallucinations. It empowers AI agents to identify complex connections among cases, statutes, and legal precedents.

Based on: Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization

HighlightCurated by Aramai Editorial

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 Editorial

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 Editorial

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

HighlightCurated by Aramai Editorial

How to Build an Adaptive AI Tutor for Any Course Using Knowledge Graph-Enhanced Retrieval-Augmented Generation (KG-RAG)

A paper introducing a novel framework for developing adaptable AI tutoring systems using knowledge graphs and retrieval-augmented generation.

The paper presents a framework called KG-RAG, which integrates structured knowledge representation with context-aware retrieval to improve AI tutoring. It addresses challenges in maintaining factual accuracy and delivering coherent instruction. The authors provide empirical validation through controlled experiments demonstrating significant learning improvements.

Based on: How to Build an Adaptive AI Tutor for Any Course Using Knowledge Graph-Enhanced Retrieval-Augmented Generation (KG-RAG)

HighlightCurated by Aramai Editorial

A stepwise intelligence generative method for structured maintenance guidance documents based on knowledge graph augmented LLM

This paper proposes a method for generating structured maintenance guidance documents using knowledge graphs and large language models.

The authors present a stepwise approach to generate structured maintenance guidance documents by augmenting a knowledge graph with a large language model. This method aims to provide accurate and informative guidance documents for maintenance tasks. The proposed approach is based on the integration of knowledge graphs and large language models, which enables the generation of high-quality content.

Based on: A stepwise intelligence generative method for structured maintenance guidance documents based on knowledge graph augmented LLM · Advanced Engineering Informatics