# SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion

arXiv: https://arxiv.org/abs/2505.07528 · HTML: https://mlsanity.com/paper/2505.07528/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 34 of its 65 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- Retrieval-augmented generation / [Hallucination detection in RAG](https://mlsanity.com/rag/hallucination-detection-in-rag/)

## Builds on (most cited first, 30 of 34)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Inspecting and Editing Knowledge Representations in Language Models](https://mlsanity.com/paper/2304.00740/) (2023)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [Information Flow Routes: Automatically Interpreting Language Models at Scale](https://mlsanity.com/paper/2403.00824/) (2024)
- [Augmenting Self-attention with Persistent Memory](https://mlsanity.com/paper/1907.01470/) (2019)
- [Cognitive Mirage: A Review of Hallucinations in Large Language Models](https://mlsanity.com/paper/2309.06794/) (2023)
- [Transformer Layers as Painters](https://mlsanity.com/paper/2407.09298/) (2024)
- [Incorporating Residual and Normalization Layers into Analysis of Masked Language Models](https://mlsanity.com/paper/2109.07152/) (2021)
- [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://mlsanity.com/paper/2401.07883/) (2024)
- [InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers](https://mlsanity.com/paper/2403.02889/) (2024)
- [Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer](https://mlsanity.com/paper/2502.12964/) (2025)
- [Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment](https://mlsanity.com/paper/2408.12194/) (2024)
- [Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2501.09997/) (2025)

## Built on by (most cited first, 3 of 3)

- [LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals](https://mlsanity.com/paper/2509.21875/) (2025)
- [Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment](https://mlsanity.com/paper/2512.09148/) (2025)
- [Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations](https://mlsanity.com/paper/2605.26362/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) models frequently encounter hallucination phenomena when integrating external information with internal parametric knowledge. Empirical studies demonstrate that the disequilibrium between external contextual information and internal parametric knowledge constitutes a primary factor in hallucination generation. Existing hallucination detection methodologies predominantly emphasize either the external or internal mechanism in isolation, thereby overlooking their synergistic effects. The recently proposed ReDeEP framework decouples these dual mechanisms, identifying two critical contributors to hallucinations: excessive reliance on parametric knowledge encoded in feed-forward networks (FFN) and insufficient utilization of external information by attention mechanisms (particularly copy heads). ReDeEP quantitatively assesses these factors to detect hallucinations and dynamically modulates the contributions of FFNs and copy heads to attenuate their occurrence. Nevertheless, ReDeEP and numerous other hallucination detection approaches have been employed at logit-level uncertainty estimation or language-level self-consistency evaluation, inadequately address the semantic dimensions of model responses, resulting in inconsistent hallucination assessments in RAG implementations. Building upon ReDeEP's foundation, this paper introduces SEReDeEP, which enhances computational processes through semantic entropy captured via trained linear probes, thereby achieving hallucination assessments that more accurately reflect ground truth evaluations.