mlsanityData to 14 Oct 2026

DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search

arXiv 2508.20353 ↗First posted 28 Aug 2025cs.LG cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37% in knowledge classification accuracy, 5.38% in retrieval recall, and 6.45% in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code are anonymous available at https://anonymous.4open.science/r/DFAMS/

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 46 of its 81 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

46 of 81 references.

References · 46

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2023Qwen Technical Reportcited by 3,344
  7. 2019Advances and Open Problems in Federated Learningcited by 3,046
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  11. 2021Knowledge Neurons in Pretrained Transformerscited by 601
  12. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
34 more
  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  2. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  3. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 281
  4. 2020MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformerscited by 245
  5. 2024Retrieval Head Mechanistically Explains Long-Context Factualitycited by 232
  6. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  7. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  8. 2020Neuron Shapley: Discovering the Responsible Neuronscited by 98
  9. 2023A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysiscited by 89
  10. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  11. 2018How Important Is a Neuron?cited by 73
  12. 2024Attention Heads of Large Language Models: A Surveycited by 67
  13. 2025Which Attention Heads Matter for In-Context Learning?cited by 61
  14. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 51
  15. 2021Differentially Private Federated Knowledge Graphs Embeddingcited by 45
  16. 2024UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systemscited by 38
  17. 2024Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysiscited by 31
  18. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 29
  19. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  20. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
  21. 2025LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Modelscited by 23
  22. 2023EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Modelscited by 19
  23. 2024TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Treescited by 19
  24. 2024TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidationcited by 18
  25. 2024Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neuronscited by 16
  26. 2025Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuningcited by 16
  27. 2025Recurrent Knowledge Identification and Fusion for Language Model Continual Learningcited by 15
  28. 2024Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuningcited by 14
  29. 2022DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Settingcited by 12
  30. 2020Privacy-preserving Decentralized Aggregation for Federated Learningcited by 10
  31. 2025Federated Retrieval Augmented Generation for Multi-Product Question Answeringcited by 10
  32. 2025EnronQA: Towards Personalized RAG over Private Documentscited by 9
  33. 2025LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Modelscited by 8
  34. 2024Shapley Pruning for Neural Network Compressioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuningcited by 5
  2. 2026Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
  2. 2026FD-RAG: Federated Dual-System Retrieval-Augmented Generation
  3. 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
  4. 2025Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG
  5. 2025DMA: Online RAG Alignment with Human Feedback
  6. 2025LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
  7. 2025Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
  8. 2026FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow