Article

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation

2025-07-03

Abstract excerpt

<title>Abstract</title> <p>Retrieval-augmented generation (RAG) has become a common strategy for updating large language model (LLM) responses with current, external information. However, models may still rely on memorized training data, bypass the retrieved evidence, and produce contaminated outputs. We introduce Retrieval-Path Contamination Scoring (RePCS), a diagnostic method that detects such behavior without...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b27b4d79-e06e-5235-a0f4-05395e666ce8
DOI: 10.21203/rs.3.rs-6992096/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented GenerationDOI 10.21203/rs.3.rs-6992096/v1Read

Basics of Large Language Models - transformers to LLMsSemantic proximity Read

Limits of Self-Correction in LLMs: An Information-Theoretic Analysis of Correlated ErrorsSemantic proximity Read

Dynamic Probabilistic Contextual Realignment in Transformer-Based Large Language Models for Semantic ConsistencySemantic proximity Read

Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented GenerationSemantic proximity Read

Learning to Retrieve, Generate, and Compress: A Unified View of Efficient RAGSemantic proximity Read

A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity Read

A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity Read

Signed Layer-Level Evidence in Transformer Predictions, and a Diagnostic for When It AppliesSemantic proximity Read

From Illusion to Insight: A Taxonomic Survey of Hallucination Mitigation Techniques in LLMsSemantic proximity Read

The Economics of Accuracy for Medical Reasoning with Large Language ModelsSemantic proximity Read

Upscaling A Smaller LLM to More Parameters via Manual Regressive DistillationSemantic proximity Read

Reverse Prompting: A Memory-Efficient Paradigm for LLM Agents Through Structural RegenerationSemantic proximity Read