HighlightCurated by Aramai Editorial

Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation

A proposed system for generating faithful and unbiased patent responses using a knowledge graph and retrieval augmented generation.

The authors propose the Patent Response System Optimised for Faithfulness (PRO), which incorporates procedural knowledge and uses a tailored large language model to generate patent responses. PRO outperforms GPT-4 in terms of faithfulness, reducing unfaithfulness across six error types. The system's effectiveness is demonstrated through experimental results.

Based on: Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation

HighlightCurated by Aramai Editorial

WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs

A paper proposing a new approach to integrating web search and knowledge graphs into retrieval-augmented generation systems.

The authors propose WeKnow-RAG, a system that combines knowledge graphs with dense vector retrieval to improve the accuracy and reliability of large language models. The approach utilizes domain-specific knowledge graphs and multi-stage web page retrieval techniques to enhance performance on factual information and complex reasoning tasks. A self-assessment mechanism is also integrated to evaluate the trustworthiness of generated answers.

Based on: WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs · arXiv (Cornell University)

HighlightCurated by Aramai Editorial

Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design

Paper exploring the use of large language models in materials analysis, design, and manufacturing.

The paper presents a fine-tuned model, MechGPT, developed for mechanics of materials domain. It explores retrieval-augmented Ontological Knowledge Graph strategies to address limitations of LLMs when queried outside learned context. The approach improves generative performance and provides mechanistic insights for material design process.

Based on: Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design · ACS Engineering Au

HighlightCurated by Aramai Editorial

CRP-RAG: A Retrieval-Augmented Generation Framework for Supporting Complex Logical Reasoning and Knowledge Planning

A framework that enhances Large Language Models by retrieving relevant knowledge.

The CRP-RAG framework addresses limitations in existing Retrieval-Augmented Generation methods. It employs reasoning graphs to model complex query reasoning processes and guides knowledge retrieval, aggregation, and evaluation through these graphs. This approach outperforms baseline models in open-domain QA, multi-hop reasoning, and factual verification.

Based on: CRP-RAG: A Retrieval-Augmented Generation Framework for Supporting Complex Logical Reasoning and Knowledge Planning · Electronics

HighlightCurated by Aramai Editorial

Graph Retrieval-Augmented Generation for Large Language Models: A Survey

A survey on incorporating Knowledge Graphs with Large Language Model Retrieval-Augmented Generation.

The paper surveys work that combines Knowledge Graphs with Large Language Model Retrieval-Augmented Generation to optimize model performance. It highlights the importance of precise document selection and noise-free corpora for expert tasks. The authors aim to provide a comprehensive understanding of this research area for future work.

Based on: Graph Retrieval-Augmented Generation for Large Language Models: A Survey

HighlightCurated by Aramai Editorial

Performance comparison of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retrieval

Paper comparing the performance of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retriev

This paper compares the effectiveness of two approaches to retrieving construction safety management knowledge: retrieval-augmented generation (RAG) and fine-tuning large language models. The study evaluates their performance in a specific domain, providing insights into their strengths and weaknesses. The results can inform the development of more efficient knowledge retrieval systems.

Based on: Performance comparison of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retrieval · Automation in Construction

HighlightCurated by Aramai Editorial

Scalable Extraction and Adoption of Shapes for Improving Data Quality and Query Processing in Knowledge Graphs

A thesis proposing techniques to improve data quality, efficient data access, and interoperability in Knowledge Graphs.

The resource proposes Quality Shapes Extraction (QSE) and SHACTOR to enhance data quality in Knowledge Graphs. It also introduces 'shapes statistics' for optimizing SPARQL query processing over KGs. The approach is demonstrated on both synthetic and real-world datasets, showing potential improvements in query performance.

Based on: Scalable Extraction and Adoption of Shapes for Improving Data Quality and Query Processing in Knowledge Graphs

HighlightCurated by Aramai Editorial

Enhancing Vector based Retrieval Augmented Generation with Contextual Knowledge Graph Construction

A novel approach to enhancing vector-based RAG models using contextual knowledge graph construction.

The authors introduce Contextual Knowledge Graph Construction (CKGC), a method that dynamically builds a knowledge graph to enhance information retrieval and question answering tasks. CKGC leverages text chunking, large language models, and ontology mapping to construct a contextualized knowledge graph. Experiments demonstrate significant improvements in Mean Reciprocal Rank and Top-k Accuracy.

Based on: Enhancing Vector based Retrieval Augmented Generation with Contextual Knowledge Graph Construction

HighlightCurated by Aramai Editorial

StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation

A method for constructing knowledge graphs to enhance retrieval-augmented generation.

This paper presents StructuGraphRAG, a method that leverages document structures to inform the extraction process and constructs knowledge graphs. The approach is designed to enhance retrieval-augmented generation (RAG) for social science research. Experimental results show improved accuracy, comprehensiveness, and contextual relevance compared to traditional RAG methods.

Based on: StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation · Proceedings of the AAAI Symposium Series

HighlightCurated by Aramai Editorial

Evaluating FAIR Digital Object and Linked Data as distributed object systems

A paper evaluating the FAIR Digital Object concept and its implementations.

The authors evaluate FAIR Digital Object (FDO) as a global distributed object system using five conceptual frameworks. They compare FDO with established Linked Data practices and Web architecture, providing recommendations for both communities. The paper discusses the history of the Semantic Web and its relevance to FDO adoption.

Based on: Evaluating FAIR Digital Object and Linked Data as distributed object systems · PeerJ Computer Science

HighlightCurated by Aramai Editorial

Shedding light on ai in radiology: A systematic review and taxonomy of eye gaze-driven interpretability in deep learning

A systematic review and taxonomy of eye gaze-driven interpretability in deep learning for radiology.

This paper conducts a systematic literature review to investigate the use of eye-tracking data in deep-learning architectures for radiology applications. The authors analyze 60 studies and propose a taxonomy to categorize the value of eye movement in different tasks. They also explore how eye gaze data can promote explainability in radiology.

Based on: Shedding light on ai in radiology: A systematic review and taxonomy of eye gaze-driven interpretability in deep learning · European Journal of Radiology

HighlightCurated by Aramai Editorial

Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering

A novel customer service question-answering method that amalgamates RAG with a knowledge graph.

The paper introduces a method that constructs a knowledge graph from historical issues to improve retrieval accuracy and answering quality. It combines retrieval-augmented generation (RAG) with a knowledge graph, preserving intra-issue structure and inter-issue relations. Empirical assessments show improved performance over baseline methods in key metrics.

Based on: Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering