The field of natural language processing is witnessing significant advancements in retrieval-augmented generation (RAG) and knowledge graphs. Recent studies have explored the potential of RAG in enhancing the factuality and accuracy of large language models. The integration of knowledge graphs with RAG has shown promising results in improving the efficiency and effectiveness of information retrieval. Notably, the development of novel frameworks such as xpSHACL, KGRAG-Ex, and CUE-RAG has enabled the creation of more accurate and explainable RAG systems. Additionally, research on graph-based retrieval and multi-agent frameworks has led to significant improvements in the detection of misinformation and the verification of multimedia content. Overall, the field is moving towards the development of more robust, efficient, and interpretable RAG systems that can leverage the strengths of both language models and knowledge graphs. Some noteworthy papers include xpSHACL, which presents an explainable SHACL validation system, and CUE-RAG, which proposes a novel approach to graph-based RAG. RAMA is also notable for its multi-agent framework designed for verifying multimedia misinformation.
Advancements in Retrieval-Augmented Generation and Knowledge Graphs
Sources
AI Feedback Enhances Community-Based Content Moderation through Engagement with Counterarguments
xpSHACL: Explainable SHACL Validation using Retrieval-Augmented Generation and Large Language Models
KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations
CUE-RAG: Towards Accurate and Cost-Efficient Graph-Based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving
RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking
Knowledge Conceptualization Impacts RAG Efficacy
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking
Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG
Truth Sleuth and Trend Bender: AI Agents to fact-check YouTube videos and influence opinions
Generating Dynamic Graph Algorithms for Multiple Backends for a Graph DSL
Multimodal Coordinated Online Behavior: Trade-offs and Strategies
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
Bridging the Gap: Leveraging Retrieval-Augmented Generation to Better Understand Public Concerns about Vaccines
Making Language Model a Hierarchical Classifier and Generator