Data to 7 Oct 2026

Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training

arXiv 2405.20978 ↗First posted 31 May 2024cs.AIcited by 88

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more

Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses. Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from real-world retrieval environments and limiting practical applicability. In this study, we initially investigate retrieval noises and categorize them into three distinct types, reflecting real-world environments. We analyze the impact of these various retrieval noises on the robustness of LLMs. Subsequently, we propose a novel RAG approach known as Retrieval-augmented Adaptive Adversarial Training (RAAT). RAAT leverages adaptive adversarial training to dynamically adjust the model's training process in response to retrieval noises. Concurrently, it employs multi-task learning to ensure the model's capacity to internally recognize noisy contexts. Extensive experiments demonstrate that the LLaMA-2 7B model trained using RAAT exhibits significant improvements in F1 and EM scores under diverse noise conditions. For reproducibility, we release our code and data at: https://github.com/calubkk/RAAT.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 39 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

34 of 39 references.

Closest ancestors · 1

Same direction, newest first

2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 33

2020Language Models are Few-Shot Learnerscited by 32,199
2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
2014Explaining and Harnessing Adversarial Examplescited by 7,287
2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
2023Qwen Technical Reportcited by 3,273
2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
2016Adversarial Machine Learning at Scalecited by 934
2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820

21 more

2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
2023Large Language Models for Information Retrieval: A Surveycited by 331
2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
2022Large Language Models with Controllable Working Memorycited by 169
2020InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspectivecited by 92
2023Knowledge is a Region in Weight Space for Fine-tuned Language Modelscited by 58
2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
2023ALCUNA: Large Language Models Meet New Knowledgecited by 35
2021Achieving Model Robustness through Discrete Adversarial Trainingcited by 23
2017Robust Multilingual Part-of-Speech Tagging via Adversarial Trainingcited by 21
2023"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 47; 2026: 30.

88 papers.

Sort:

By area:

38 more

2025cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Treecited by 17
2024Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuningcited by 14
2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learningcited by 14
2025Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generationcited by 13
2025Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Modelscited by 13
2025Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAGcited by 13
2024Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Modelscited by 12
2024PA-RAG: RAG Alignment via Multi-Perspective Preference Optimizationcited by 11
2025Out of Style: RAG's Fragility to Linguistic Variationcited by 10
2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Levelcited by 10
2025RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimizationcited by 9
2025Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Modelscited by 9
2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Modelscited by 8
2025Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGcited by 8
2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledgecited by 7
2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
2025Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approachcited by 6
2025Influence Guided Context Selection for Effective Retrieval-Augmented Generationcited by 6
2026Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generationcited by 6
2025RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answeringcited by 5
2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimizationcited by 5
2025A Survey on Proactive Defense Strategies Against Misinformation in Large Language Modelscited by 5
2025Conflict-Aware Soft Prompting for Retrieval-Augmented Generationcited by 5
2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
2026NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systemscited by 5
2026Retrieval as Generation: A Unified Framework with Self-Triggered Information Planningcited by 5
2026Safety and accuracy follow different scaling laws in clinical large language modelscited by 5
2025EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generationcited by 4
2025Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entitiescited by 4
2025Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agentscited by 4
2024DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generationcited by 3
2025CUB: Benchmarking Context Utilisation Techniques for Language Modelscited by 3
2025RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generationcited by 3
2026Better and Worse with Scale: How Contextual Entrainment Diverges with Model Sizecited by 3
2024RASTeR: Robust, Agentic, and Structured Temporal Reasoningcited by 2
2025Evaluating the Retrieval Robustness of Large Language Modelscited by 2
2025Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguitycited by 2

50 most cited of 88 All 88 (JSON)

Similar, not cited

Close in wording, no citation either way