mlsanityData to 14 Oct 2026

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

arXiv 2305.14292 ↗First posted 23 May 2023cs.CLcited by 67

Not on the map. Why?

Abstract (arXiv)

This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus. WikiChat generates a response from an LLM, retains only the grounded facts, and combines them with additional information it retrieves from the corpus to form factual and engaging responses. We distill WikiChat based on GPT-4 into a 7B-parameter LLaMA model with minimal loss of quality, to significantly improve its latency, cost and privacy, and facilitate research and deployment. Using a novel hybrid human-and-LLM evaluation methodology, we show that our best system achieves 97.3% factual accuracy in simulated conversations. It significantly outperforms all retrieval-based and LLM-based baselines, and by 3.9%, 38.6% and 51.0% on head, tail and recent knowledge compared to GPT-4. Compared to previous state-of-the-art retrieval-based chatbots, WikiChat is also significantly more informative and engaging, just like an LLM. WikiChat achieves 97.9% factual accuracy in conversations with human users about recent topics, 55.0% better than GPT-4, while receiving significantly higher user ratings and more favorable comments.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 38 of its 93 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

38 of 93 references.

References · 38

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  3. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  6. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  9. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
26 more
  1. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  3. 2020Recipes for building an open-domain chatbotcited by 593
  4. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  5. 2021Editing Factual Knowledge in Language Modelscited by 553
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2022Memory-Based Model Editing at Scalecited by 447
  8. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  9. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  10. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  11. 2023AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotatorscited by 172
  12. 2022A Survey on Retrieval-Augmented Text Generationcited by 158
  13. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  14. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
  15. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 119
  16. 2019Fine-grained Fact Verification with Kernel Graph Attention Networkcited by 105
  17. 2019Assessing The Factual Accuracy of Generated Textcited by 103
  18. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  19. 2022PLAID: An Efficient Engine for Late Interaction Retrievalcited by 101
  20. 2019ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisonscited by 83
  21. 2022AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversationcited by 79
  22. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 77
  23. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
  24. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  25. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 53
  26. 2022Transfer Learning Approaches for Building Cross-Language Dense Retrieval Modelscited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 36; 2025: 22; 2026: 4.

67 papers.

Sort:

By area:

  1. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 267
  2. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  3. 2024Language Models with Conformal Factuality Guaranteescited by 131
  4. 2024BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Modelscited by 86
  5. 2024Unified Hallucination Detection for Multimodal Large Language Modelscited by 75
  6. 2023Do Androids Know They're Only Dreaming of Electric Sheep?cited by 67
  7. 2025A Survey of Large Language Model Agents for Question Answeringcited by 48
  8. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  9. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  10. 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillationcited by 32
  11. 2024Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systemscited by 27
  12. 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
38 more
  1. 2024KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checkingcited by 26
  2. 2024Prompting open-source and commercial language models for grammatical error correction of English learner textcited by 24
  3. 2024Jill Watson: A Virtual Teaching Assistant powered by ChatGPTcited by 24
  4. 2024DataGen: Unified Synthetic Dataset Generation via Large Language Modelscited by 23
  5. 2024Data Extraction Attacks in Retrieval-Augmented Generation via Backdoorscited by 23
  6. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 23
  7. 2024A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagationcited by 21
  8. 2024Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citationscited by 15
  9. 2024Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrievalcited by 14
  10. 2024ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Modelscited by 14
  11. 2025COVE: COntext and VEracity prediction for out-of-context imagescited by 14
  12. 2023SUQL: Conversational Search over Structured and Unstructured Data with Large Language Modelscited by 13
  13. 2024Web Retrieval Agents for Evidence-Based Misinformation Detectioncited by 13
  14. 2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsingcited by 11
  15. 2025Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generationcited by 11
  16. 2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
  17. 2024ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questionscited by 10
  18. 2024Panacea: A foundation model for clinical trial search, summarization, design, and recruitmentcited by 10
  19. 2024Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wildcited by 9
  20. 2024MOPO: Multi-Objective Prompt Optimization for Affective Text Generationcited by 9
  21. 2025Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AIcited by 9
  22. 2024A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challengescited by 8
  23. 2024Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systemscited by 8
  24. 2024Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestrycited by 7
  25. 2024Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorercited by 7
  26. 2024A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Modelscited by 6
  27. 2024Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responsescited by 6
  28. 2025Domain Regeneration: How well do LLMs match syntactic properties of text domains?cited by 6
  29. 2024KGValidator: A Framework for Automatic Validation of Knowledge Graph Constructioncited by 5
  30. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  31. 2024Assessing Generalization for Subpopulation Representative Modeling via In-Context Learningcited by 4
  32. 2025Wikipedia in the Era of LLMs: Evolution and Riskscited by 4
  33. 2025Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Modelscited by 4
  34. 2023An Empathetic User-Centric Chatbot for Emotional Supportcited by 3
  35. 2025Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAGcited by 3
  36. 2025EmoRAG: Evaluating RAG Robustness to Symbolic Perturbationscited by 3
  37. 2024Enhancing LLM's Cognition via Structurizationcited by 2
  38. 2025Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inferencecited by 2

50 most cited of 67 All 67 (JSON)