HighlightCurated by Aramai EditorialarXiv

Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!

Paper on improving question answering systems with large language models using ontologies.

This paper presents an approach to improve the accuracy of question answering systems with large language models by leveraging ontologies. The authors propose a method that consists of ontology-based query check and LLM repair, which increases the overall accuracy to 72%. The results provide further evidence that investing knowledge graphs, namely the ontology, provides higher accuracy for LLM-powered question-answering systems.

Based on: Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue! · arxiv.org

HighlightCurated by Aramai EditorialarXiv

Skill Retrieval Augmentation for Agentic AI

A paper proposing a paradigm for dynamically retrieving and incorporating skills in large language models.

The authors introduce Skill Retrieval Augmentation (SRA), a method for agents to retrieve relevant skills from external corpora on demand. They construct a benchmark, SRA-Bench, to evaluate the full SRA pipeline. The paper shows that retrieval-based skill augmentation can improve agent performance and highlights the need for more efficient skill incorporation.

Based on: Skill Retrieval Augmentation for Agentic AI · arXiv

HighlightCurated by Aramai EditorialarXiv

Separating Semantic Competition from Context Length in RAG Reading

Paper on evaluating Retrieval-Augmented Generation (RAG) systems.

The authors introduce a matched-control protocol to isolate the effect of semantic competition on RAG reading performance. They apply this protocol to two compact open models on SQuAD and report improvements in F1, answer inclusion, and exact match scores. The results suggest that the competition effect is distinct from context length.

Based on: Separating Semantic Competition from Context Length in RAG Reading · arXiv

HighlightCurated by Aramai EditorialarXiv

An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

A paper proposing an agent-oriented pluggable retrieval orchestration layer for experience-driven retrieval strategy selection.

The authors present Experience-RAG Skill, a layer positioned between the agent and retriever pool. It analyzes the scene, consults an experience memory, selects a retrieval strategy, and returns structured evidence to the agent. The proposed skill outperforms fixed single-retriever baselines on various tasks.

Based on: An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration · arXiv

HighlightCurated by Aramai EditorialarXiv

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

A training-free hybrid retrieval framework for Retrieval Augmented Generation (RAG).

The authors propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation. UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities, estimating reliability from distribution entropy and fusing candidates according to query-specific semantic, lexical, and granularity confidence.

Based on: Uncertainty-Aware Hybrid Retrieval for Long-Document RAG · arXiv

HighlightCurated by Aramai EditorialarXiv

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning

A framework for improving the reliability of reasoning language models through error checking and correction.

CheckRLM proposes a framework to improve the reliability of reasoning language models by timely checking and correcting factual errors. It extracts claims from the reasoning chain, identifies inconsistencies, and performs minimal-cost corrections using external knowledge. The framework demonstrates strong capability in mitigating error accumulation in long-horizon reasoning with lower costs.

Based on: CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning · arXiv

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 EditorialProceedings of the AAAI Conference on Artificial Intelligence

TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs

A framework for resolving factual conflicts between LLMs' internal knowledge and external information using knowledge graphs.

This paper proposes TruthfulRAG, a framework that leverages knowledge graphs to resolve factual conflicts in RAG systems. It constructs KGs from retrieved content, identifies relevant knowledge through query-based graph retrieval, and employs entropy-based filtering mechanisms to mitigate inconsistencies. The authors claim that TruthfulRAG outperforms existing methods in resolving knowledge conflicts and improving the robustness of RAG systems.

Based on: TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs · Proceedings of the AAAI Conference on Artificial Intelligence

HighlightCurated by Aramai EditorialarXiv

Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models

A paper proposing a framework for automating cause-and-effect logic generation using knowledge graphs and large language models.

The authors present a semantic-AI framework that combines a knowledge graph with a constrained large language model to automate the generation of cause-and-effect logic. The framework builds on an established modular alignment ontology and demonstrates its application on a modular process plant. This approach aims to reduce manual effort in creating engineering specifications.

Based on: Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models · arXiv

HighlightCurated by Aramai EditorialarXiv

Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs

A paper proposing a modular pipeline for building a travel-domain reasoning LLM grounded in an expert-designed knowledge graph.

The authors propose a modular pipeline to build a travel-domain reasoning large language model (LLM) using a domain-specific knowledge graph. The pipeline integrates a travel KG, bottom-up construction procedure, and supervised fine-tuning stage to embed domain knowledge into the LLM. The approach achieves high accuracy on a benchmark dataset.

Based on: Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs · arXiv

HighlightCurated by Aramai EditorialarXiv

XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation

A framework that generates causally grounded explanations for GraphRAG systems.

The paper introduces XGRAG, a graph-native framework for explaining knowledge graph-based retrieval-augmented generation. It employs graph-based perturbation strategies to quantify the contribution of individual graph components on the model answer. The authors conduct experiments comparing XGRAG against an existing explainability baseline and evaluate its robustness across various question types and LLMs.

Based on: XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation · arXiv