mlsanityData to 14 Oct 2026

From RAG to RICHES: Retrieval Interlaced with Sequence Generation

arXiv 2407.00361 ↗First posted 29 Jun 2024cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We present RICHES, a novel approach that interleaves retrieval with sequence generation tasks. RICHES offers an alternative to conventional RAG systems by eliminating the need for separate retriever and generator. It retrieves documents by directly decoding their contents, constrained on the corpus. Unifying retrieval with generation allows us to adapt to diverse new tasks via prompting alone. RICHES can work with any Instruction-tuned model, without additional training. It provides attributed evidence, supports multi-hop retrievals and interleaves thoughts to plan on what to retrieve next, all within a single decoding pass of the LLM. We demonstrate the strong performance of RICHES across ODQA tasks including attributed and multi-hop QA.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

31 of 43 references.

References · 31

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  8. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  9. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
19 more
  1. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  2. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  3. 2020Autoregressive Entity Retrievalcited by 334
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  5. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  6. 2022Teaching language models to support answers with verified quotescited by 292
  7. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  8. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  9. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  10. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  11. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 154
  12. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
  13. 2023InstructRetro: Instruction Tuning post Retrieval-Augmented Pretrainingcited by 53
  14. 2023How Does Generative Retrieval Scale to Millions of Passages?cited by 48
  15. 2017Deep Reinforcement Learning-based Image Captioning with Embedding Rewardcited by 40
  16. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  17. 2022PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognitioncited by 29
  18. 2021Boosting Search Engines with Interactive Agentscited by 19
  19. 20231-PAGER: One Pass Answer Generation and Evidence Retrievalcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  2. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  3. 2024OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMscited by 14
  4. 2025Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Enginescited by 13
  5. 2025VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documentscited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2024The Power of Noise: Redefining Retrieval for RAG Systems
  2. 2024Toward Optimal Search and Retrieval for RAG
  3. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  4. 2025Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries
  5. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  6. 2025Less LLM, More Documents: Searching for Improved RAG
  7. 2025ImpRAG: Retrieval-Augmented Generation with Implicit Queries
  8. 2024FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG