M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
arXiv preprint arXiv:2506.00054 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of parametric knowledge storage-such as factual inconsistency and domain inflexibility-it introduces new challenges in retrieval quality, grounding fidelity, pipeline efficiency, and robustness against noisy or adversarial inputs. This survey provides a comprehensive synthesis of recent advances in RAG systems, offering a taxonomy that categorizes architectures into retriever-centric, generator-centric, hybrid, and robustness-oriented designs. We systematically analyze enhancements across retrieval optimization, context filtering, decoding control, and efficiency improvements, supported by comparative performance analyses on short-form and multi-hop question answering tasks. Furthermore, we review state-of-the-art evaluation frameworks and benchmarks, highlighting trends in retrieval-aware evaluation, robustness testing, and federated retrieval settings. Our analysis reveals recurring trade-offs between retrieval precision and generation flexibility, efficiency and faithfulness, and modularity and coordination. We conclude by identifying open challenges and future research directions, including adaptive retrieval architectures, real-time retrieval integration, structured reasoning over multi-hop evidence, and privacy-preserving retrieval mechanisms. This survey aims to consolidate current knowledge in RAG research and serve as a foundation for the next generation of retrieval-augmented language modeling systems.
representative citing papers
TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
Proposes High-Precision Scoring (HPS) and Tie-aware Retrieval Metrics (TRM) to reduce tie-induced instability in low-precision retrieval evaluation.
Hybrid RAG over UK public health guidance sharply raises MCQA accuracy and free-form faithfulness, letting smaller open models match larger closed models without retrieval.
Schema-First Retrieval embeds catalog metadata rather than rows and uses parallel retrieval plus reranking to raise table and column recall and cut SQL execution errors on three benchmarks.
VikingMem implements the Memory Base paradigm via event-centric extraction and entity updates on VikingDB with temporal compression, claiming up to 30% better retrieval effectiveness on long-term memory benchmarks.
RAG frequently degrades LLM malware explanations when structured VirusTotal input is already available by introducing irrelevant context and narrative noise.
Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.
SLOT organizes RAG security literature by attack Surface, defense Layer, CIA Objective, and Target scope, exposing mismatches between attacks and defenses along a six-stage knowledge pipeline.
A RAG system with query-based log filtering achieves up to 94% recall in malware incident analysis and 96% attack-step detection, with ablation studies confirming the filtering step is essential.
citing papers explorer
-
M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
-
Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Reliable Evaluation Protocol for Low-Precision Retrieval
Proposes High-Precision Scoring (HPS) and Tie-aware Retrieval Metrics (TRM) to reduce tie-induced instability in low-precision retrieval evaluation.
-
Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
Hybrid RAG over UK public health guidance sharply raises MCQA accuracy and free-form faithfulness, letting smaller open models match larger closed models without retrieval.
-
Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics
Schema-First Retrieval embeds catalog metadata rather than rows and uses parallel retrieval plus reranking to raise table and column recall and cut SQL execution errors on three benchmarks.
-
VikingMem: A Memory Base Management System for Stateful LLM-based Applications
VikingMem implements the Memory Base paradigm via event-centric extraction and entity updates on VikingDB with temporal compression, claiming up to 30% better retrieval effectiveness on long-term memory benchmarks.
-
Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis
RAG frequently degrades LLM malware explanations when structured VirusTotal input is already available by introducing irrelevant context and narrative noise.
-
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.
-
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
SLOT organizes RAG security literature by attack Surface, defense Layer, CIA Objective, and Target scope, exposing mismatches between attacks and defenses along a six-stage knowledge pipeline.
-
Retrieval-Augmented LLMs for Security Incident Analysis
A RAG system with query-based log filtering achieves up to 94% recall in malware incident analysis and 96% attack-step detection, with ablation studies confirming the filtering step is essential.