mlsanityData to 14 Oct 2026

PropRAG: Guiding Retrieval with Beam Search over Proposition Paths

arXiv 2504.18070 ↗First posted 25 Apr 2025cs.CL cs.AIcited by 23

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval Augmented Generation (RAG) has become the standard approach for equipping Large Language Models (LLMs) with up-to-date knowledge. However, standard RAG, relying on independent passage retrieval, often fails to capture the interconnected nature of information required for complex, multi-hop reasoning. While structured RAG methods attempt to address this using knowledge graphs built from triples, we argue that the inherent context loss of triples (context collapse) limits the fidelity of the knowledge representation. We introduce PropRAG, a novel RAG framework that shifts from triples to context-rich propositions and introduces an efficient, LLM-free online beam search over proposition paths to discover multi-step reasoning chains. By coupling a higher-fidelity knowledge representation with explicit path discovery, PropRAG achieves state-of-the-art zero-shot Recall@5 and F1 scores on 2Wiki, HotpotQA, and MuSiQue, advancing non-parametric knowledge integration by improving evidence retrieval through richer representation and efficient reasoning path discovery.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 37 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

29 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  2. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach18 Jul
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  4. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  7. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  8. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  9. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  10. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  11. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  12. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 396
13 more
  1. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  2. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  3. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 242
  4. 2024Generative Representational Instruction Tuningcited by 233
  5. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  6. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  7. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 162
  8. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  9. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  10. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 103
  11. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  12. 2019Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphscited by 53
  13. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answeringcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 18.

23 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 52
  3. 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agentscited by 32
  4. 2025GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learningcited by 12
  5. 2025HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modelingcited by 4
  6. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  7. 2026Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledgecited by 2
  8. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  9. 2026History-Conditioned Joint-Prefix Alignment for Generative Recommendationcited by 1
  10. 2026A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphscited by 0
  11. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  12. 2026RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answeringcited by 0
11 more
  1. 2026SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAGcited by 0
  2. 2026EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrievalcited by 0
  3. 2026LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Groundingcited by 0
  4. 2026The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarkscited by 0
  5. 2026Enhancing LLMs in Predictive Political QA with Semi-Structured Datacited by 0
  6. 2026LivingRAG: Augmenting Graph RAG with Experiencecited by 0
  7. 2026Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answeringcited by 0
  8. 2026HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answeringcited by 0
  9. 2026Per-Query Gating of LLM Rerankers for Multi-Hop Retrievalcited by 0
  10. 2026EvLink: Source-Grounded Evidence Linking for Graph RAGcited by 0
  11. 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  2. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  3. 2025Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
  4. 2026Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
  5. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
  6. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  7. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  8. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation