mlsanityData to 7 Oct 2026

CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG

arXiv 2609.02913 ↗First posted 14 Jul 2026cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented generation (RAG) is increasingly used in educational question answering, but standard retrievers optimize topical relevance without enforcing curriculum validity. In school settings, a passage can be relevant yet inappropriate if it comes from the wrong subject, level, or examination context; we call this failure mode curriculum leakage. We present CHSR-RRF, a curriculum-gated hybrid retrieval framework that applies metadata constraints before retrieval, then combines sparse and dense search with reciprocal rank fusion and deterministic reranking. We also introduce CERB, a 126-case benchmark for curriculum-constrained retrieval with hierarchy-aware relevance labels and explicit leakage annotations. On a 61-case pilot, pre-retrieval gating reduces leakage by 4.6x (p<0.001) while preserving ranked recall, whereas applying the same constraints after retrieval collapses recall and exact-scope success to zero (p=0.039). A full-benchmark lower-bound analysis further shows that many remaining failures arise from corpus and metadata gaps rather than retrieval design alone. These results show that retrieval in structured educational domains should be treated as constrained selection, with validity enforced when the candidate pool is formed rather than after ranking.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 62 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

34 of 62 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 32

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
20 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  2. 2019Passage Re-ranking with BERTcited by 629
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  6. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  7. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  8. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
  9. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  10. 2020Overview of the TREC 2019 deep learning trackcited by 282
  11. 2024Corrective Retrieval Augmented Generationcited by 187
  12. 2023Time Travel in LLMs: Tracing Data Contamination in Large Language Modelscited by 175
  13. 2023Investigating Data Contamination in Modern Benchmarks for Large Language Modelscited by 136
  14. 2024Benchmarking Benchmark Leakage in Large Language Modelscited by 102
  15. 2020Stance Detection on Social Media: State of the Art and Trendscited by 93
  16. 2019A Deep Look into Neural Ranking Models for Information Retrievalcited by 79
  17. 2022An Analysis of Fusion Functions for Hybrid Retrievalcited by 49
  18. 2017Query expansion techniques for information retrieval: A surveycited by 44
  19. 2021A Replication Study of Dense Passage Retrievercited by 37
  20. 2023Assigning AI: Seven Approaches for Students, with Promptscited by 16

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
  2. 2025RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
  3. 2026SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
  4. 2025Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval
  5. 2025ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning
  6. 2025Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
  7. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
  8. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU