mlsanityData to 7 Oct 2026

Reducing hallucination in structured outputs via Retrieval-Augmented Generation

arXiv 2404.08189 ↗First posted 12 Apr 2024cs.LG cs.AI cs.CLcited by 92

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI systems may face challenges in user adoption. In the process of deploying an enterprise application that produces workflows based on natural language requirements, we devised a system leveraging Retrieval Augmented Generation (RAG) to greatly improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our proposed system significantly reduces hallucinations in the output and improves the generalization of our LLM in out-of-domain settings. In addition, we show that using a small, well-trained retriever encoder can reduce the size of the accompanying LLM, thereby making deployments of LLM-based systems less resource-intensive.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 34 references that are in the map. First posted on arXiv 12 Apr 2024.

Builds on

27 of 34 references.

References · 27

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  11. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
15 more
  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  2. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  3. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  4. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  5. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  6. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  8. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  9. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  10. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  11. 2022The Stack: 3 TB of permissively licensed source codecited by 354
  12. 2022Language Models of Code are Few-Shot Commonsense Learnerscited by 160
  13. 2023Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Datacited by 23
  14. 2016Latent Attention For If-Then Program Synthesiscited by 10
  15. 2020Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesiscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 53; 2026: 28.

92 papers.

Sort:

By area:

  1. 2024MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Enginescited by 98
  2. 2025VideoRAG: Retrieval-Augmented Generation over Video Corpuscited by 55
  3. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  4. 2024Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refusecited by 33
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 26
  6. 2025Benchmarking Retrieval-Augmented Generation for Chemistrycited by 19
  7. 2025CacheClip: Accelerating RAG with Effective KV Cache Reusecited by 14
  8. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  9. 2025Out of Style: RAG's Fragility to Linguistic Variationcited by 10
  10. 2025Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucinationcited by 10
  11. 2026ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Supportcited by 10
  12. 2024A Survey on Knowledge Organization Systems of Research Fields: Resources and Challengescited by 9
38 more
  1. 2025CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generationcited by 9
  2. 2025CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoningcited by 9
  3. 2024Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistrycited by 8
  4. 2025Generative AI in Transportation Planning: A Surveycited by 8
  5. 2025HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMscited by 8
  6. 2025EnronQA: Towards Personalized RAG over Private Documentscited by 8
  7. 2025ContextPilot: Fast Long-Context Inference via Context Reusecited by 8
  8. 2024Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systemscited by 7
  9. 2025Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agentscited by 7
  10. 2025DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generationcited by 7
  11. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAGcited by 6
  12. 2025Agentic LLM Framework for Adaptive Decision Discoursecited by 6
  13. 2025Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflowscited by 6
  14. 2025Zero-shot Multimodal Document Retrieval via Cross-modal Question Generationcited by 6
  15. 2026FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAGcited by 6
  16. 2024UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrieverscited by 5
  17. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  18. 2025LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrievalcited by 5
  19. 2025Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domainscited by 5
  20. 2025Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inferencecited by 5
  21. 2025FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAGcited by 4
  22. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  23. 2026Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoningcited by 4
  24. 2024Generating a Low-code Complete Workflow via Task Decomposition and RAGcited by 3
  25. 2025SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searchescited by 3
  26. 2025When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Outputcited by 3
  27. 2025Generative AI Enhanced Financial Risk Management Information Retrievalcited by 3
  28. 2025LLM Agents Are the Antidote to Walled Gardenscited by 3
  29. 2025Combining Evidence and Reasoning for Biomedical Fact-Checkingcited by 3
  30. 2025RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generationcited by 3
  31. 2026Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selectioncited by 3
  32. 2024Learning Semantic Structure through First-Order-Logic Translationcited by 2
  33. 2025StarFlow: Generating Structured Workflow Outputs From Sketch Imagescited by 2
  34. 2025WorkTeam: Constructing Workflows from Natural Language with Multi-Agentscited by 2
  35. 2025An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answeringcited by 2
  36. 2025KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generationcited by 2
  37. 2026Fine-Tuning Language Models to Know What They Knowcited by 2
  38. 2025RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generationcited by 1

50 most cited of 92 All 92 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
  2. 2024100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
  3. 2026Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
  4. 2024RAGged Edges: The Double-Edged Sword of Retrieval-Augmented Chatbots
  5. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  6. 2024Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination
  7. 2024Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
  8. 2026Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey