mlsanityData to 14 Oct 2026

ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation

arXiv 2508.20131 ↗First posted 26 Aug 2025cs.AI cs.LGcited by 12

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 46 of its 58 references that are in the map. First posted on arXiv 26 Aug 2025.

Builds on

46 of 58 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals22 Feb
  2. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation18 Jun
  3. 2024CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG17 Jun
  4. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation9 Jun
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  6. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering6 Oct

Other references · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  11. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
28 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  3. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  4. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 435
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  6. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  7. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  8. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  9. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 211
  10. 2020How Context Affects Language Models' Factual Predictionscited by 181
  11. 2024What Evidence Do Language Models Find Convincing?cited by 75
  12. 2024Bridging the Preference Gap between Retrievers and LLMscited by 69
  13. 2024Evaluating Mathematical Reasoning Beyond Accuracycited by 69
  14. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  15. 2025Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokenscited by 41
  16. 2024Argumentative Large Language Models for Explainable and Contestable Claim Verificationcited by 36
  17. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  18. 2020A Review on Fact Extraction and Verificationcited by 29
  19. 2024RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Modelscited by 27
  20. 2025Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoningcited by 17
  21. 2023Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languagescited by 8
  22. 2025Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompletenesscited by 7
  23. 2025Evaluating open-source Large Language Models for automated fact-checkingcited by 6
  24. 2025Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMscited by 6
  25. 2024Approximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddingscited by 5
  26. 2024Conformalized Answer Set Prediction for Knowledge Graph Embeddingcited by 5
  27. 2023Robust Knowledge Extraction from Large Language Models using Social Choice Theorycited by 4
  28. 2025Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddingscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 11.

12 papers.

  1. 2025Retrieval- and Argumentation-Enhanced Multi-Agent LLMs for Judgmental Forecasting (Extended Version with Supplementary Material)cited by 8
  2. 2026Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoringcited by 5
  3. 2026Argumentation for Explainable and Globally Contestable Decision Support with LLMscited by 3
  4. 2026Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verificationcited by 2
  5. 2026AWM: Answerable Working Memory for Long-Document VQA Agentscited by 2
  6. 2026Neurosymbolic Retrievers for Retrieval-augmented Generationcited by 1
  7. 2026ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generationcited by 0
  8. 2026SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphscited by 0
  9. 2026PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updatescited by 0
  10. 2026Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordinationcited by 0
  11. 2026Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiencescited by 0
  12. 2026OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personascited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Structure-Augmented Reasoning Generation
  2. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  3. 2024Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
  4. 2026Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
  5. 2025From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs
  6. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
  7. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
  8. 2025ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation