HighlightCurated by Aramai EditorialarXiv

DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

A framework for learnable evidence control in multi-hop retrieval-augmented generation.

The paper introduces DynaKRAG, a unified framework that formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations. It uses a learned controller to select the next operation and updates the evidence state accordingly. The authors evaluate DynaKRAG on several benchmarks and demonstrate its effectiveness in coordinating retrieval, diagnosis, and gap-directed acquisition.

Based on: DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation · arXiv

HighlightCurated by Aramai EditorialIEEE Communications Magazine

Proof of Unlearning for Semantic Knowledge Bases in Large Language Models-Enabled Semantic Communication

A framework for efficiently and verifiably updating large language model-enabled semantic knowledge bases.

The authors propose a proof-of-unlearning framework for updating large language models (LLMs) used in semantic knowledge bases. The framework tracks the evolution of unlearning by measuring drifts in the LoRA adapter subspace. Experimental results demonstrate its effectiveness. This work addresses the challenge of removing outdated, malicious, or privacy-sensitive content from LLMs without retraining.

Based on: Proof of Unlearning for Semantic Knowledge Bases in Large Language Models-Enabled Semantic Communication · IEEE Communications Magazine

HighlightCurated by Aramai Editorialopenalex.org

Enhancing Operations at the Columbus Control-Center: A Hybrid Approach Utilizing Large Language Models, Knowledge Graphs, and Retrieval-Augmented Generation

A paper investigating a hybrid approach combining Large Language Models with Knowledge Graphs and Retrieval-Augmented Generation.

The paper proposes a hybrid system to enhance operational efficiency at the Columbus Control-Center, leveraging Large Language Models, Knowledge Graphs, and Retrieval-Augmented Generation. The system aims to automate routine tasks and provide real-time support for flight control teams. It combines the strengths of LLMs, KGs, and RAG to create a more intelligent and responsive support system.

Based on: Enhancing Operations at the Columbus Control-Center: A Hybrid Approach Utilizing Large Language Models, Knowledge Graphs, and Retrieval-Augmented Generation

HighlightCurated by Aramai EditorialVLDB Endowment

QSE: Extraction of Validating Shapes from Very Large Knowledge Graphs

Proposes a Quality Shapes Extraction approach for extracting validating shapes in very large knowledge graphs.

The paper presents the QSE approach, which uses SHACL/ShEx to extract validating shapes from large knowledge graphs. It provides both exact and approximate solutions with confidence metrics. The authors achieve significant speed improvements and spurious shape reductions on DBpedia.

Based on: QSE: Extraction of Validating Shapes from Very Large Knowledge Graphs · VLDB Endowment