Open-Source Reproduction and Explainability Analysis of Corrective Retrieval Augmented Generation

• URL: http://arxiv.org/abs/2603.16169v1
• Date: Tue, 17 Mar 2026 06:38:00 GMT
• Title: Open-Source Reproduction and Explainability Analysis of Corrective Retrieval Augmented Generation
• Abstract summary: We present a fully open-source reproduction of Corrective Retrieval Augmented Generation (CRAG)<n>CRAG improves robustness of RAG systems by evaluating retrieved document quality and triggering corrective actions.<n>We replace proprietary web search with the Wikipedia API and the original LLaMA-2 generator with Phi-3-mini-4k-instruct.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Corrective Retrieval Augmented Generation (CRAG) improves the robustness of RAG systems by evaluating retrieved document quality and triggering corrective actions. However, the original implementation relies on proprietary components including the Google Search API and closed model weights, limiting reproducibility. In this work, we present a fully open-source reproduction of CRAG, replacing proprietary web search with the Wikipedia API and the original LLaMA-2 generator with Phi-3-mini-4k-instruct. We evaluate on PopQA and ARC-Challenge, demonstrating that our open-source pipeline achieves comparable performance to the original system. Furthermore, we contribute the first explainability analysis of CRAG's T5-based retrieval evaluator using SHAP, revealing that the evaluator primarily relies on named entity alignment rather than semantic similarity. Our analysis identifies key failure modes including domain transfer limitations on science questions. All code and results are available at https://github.com/suryayalavarthi/crag-reproduction.

Related papers

• Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach [0.0]
  This work evaluates a simple and interpretable modification to RAG retrieval ranking that incorporates provenance-informed source reliability priors.<n>The framework is evaluated against a similarity-only baseline on a 120-document health-domain corpus.<n> source-aware reranking improves Precision@5 from 0.48 to 0.72 and reduces average adversarial document retrieval.
  arXiv  Detail & Related papers  (2026-06-08T14:09:04Z)
• RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation [1.564663326217051]
  RAGVUE is a framework for evaluation of Retrieval-Augmented Generation (RAG) systems.<n>It decomposes RAG behavior into retrieval quality, answer relevance and completeness, strict claim-level faithfulness, and judge calibration.<n> RAGVUE supports both manual metric selection and fully automated agentic evaluation.
  arXiv  Detail & Related papers  (2025-12-03T07:42:49Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking [23.982187522815536]
  HiChunk is a multi-level document structuring framework based on fine-tuned LLMs and the Auto-Merge retrieval algorithm.<n>HiChunk achieves better chunking quality within reasonable time consumption, thereby enhancing the overall performance of RAG systems.
  arXiv  Detail & Related papers  (2025-09-15T03:32:50Z)
• SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment [49.86376148975563]
  Large language models (LLMs) have revolutionized natural language processing through their capabilities in understanding and executing diverse tasks.<n> supervised fine-tuning, particularly in Retrieval-Augmented Generation (RAG) scenarios, often leads to catastrophic forgetting.<n>We propose SelfAug, a self-distribution alignment method that aligns input sequence logits to preserve the model's semantic distribution.
  arXiv  Detail & Related papers  (2025-09-04T06:50:47Z)
• Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation [52.3707788779464]
  We introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD)<n>ARC-JSD enables efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling.<n> Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements.
  arXiv  Detail & Related papers  (2025-05-22T09:04:03Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• SiReRAG: Indexing Similar and Related Information for Multihop Reasoning [96.60045548116584]
  SiReRAG is a novel RAG indexing approach that explicitly considers both similar and related information.<n>SiReRAG consistently outperforms state-of-the-art indexing methods on three multihop datasets.
  arXiv  Detail & Related papers  (2024-12-09T04:56:43Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation [42.82192656794179]
  Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in unseen scenarios. Retrieval-Augmented Generation (RAG) addresses this by incorporating external, relevant documents into the response generation process.
  arXiv  Detail & Related papers  (2024-03-31T08:58:54Z)
• Corrective Retrieval Augmented Generation [36.04062963574603]
  Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
  arXiv  Detail & Related papers  (2024-01-29T04:36:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.