AI Wiki — Knowledge Base

Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries

arXiv:2608.26385v1 Announce Type: cross Abstract: Volume-based accuracy rewards retrieval-augmented generation (RAG) systems for guessing: a system that answers everything outscores one that declines

model-releasesarxiv-cs-ai

28 Aug 2026

Search: “rag”

RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems

Is Agentic RAG worth it? An experimental comparison of RAG approaches

post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at Synthesis

CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG

HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation

PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation

NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering

H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations

RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation

MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers

PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models

HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG

Domain-oriented RAG Assessment (DoRA): Synthetic Benchmarking for RAG-based Question Answering on Defense Documents

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models

R^{2}Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG

Next-Gen Sponsored Search: Crafting the Perfect Query with Inventory-Aware RAG (InvAwr-RAG) Based GenAI

Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization

Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG

Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)

ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation

AkasicDB: Demonstrating Omni RAG with a Unified Vector-Graph-Relational DBMS

TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation

RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety

CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG

MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval

FD-RAG: Federated Dual-System Retrieval-Augmented Generation

Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation

MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation

M^3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees

CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering

When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies

Which RAG Paradigm Wins at Scale? A Scaling Study of Retrieval-Augmented Generation Paradigms

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

In-depth Analysis of Graph-based RAG in a Unified Framework

Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines

HaS: Accelerating RAG through Homology-Aware Speculative Retrieval

Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries

The RAT: A Unified Bayesian Model for RAG Evaluation