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

arXiv: https://arxiv.org/abs/2305.14292 · HTML: https://mlsanity.com/paper/2305.14292/

## 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 (most cited first, 30 of 38)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators](https://mlsanity.com/paper/2303.16854/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)
- [Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering](https://mlsanity.com/paper/2104.08202/) (2021)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://mlsanity.com/paper/1910.09796/) (2019)
- [Assessing The Factual Accuracy of Generated Text](https://mlsanity.com/paper/1905.13322/) (2019)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)

## Built on by (most cited first, 30 of 67)

- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models](https://mlsanity.com/paper/2406.00083/) (2024)
- [Unified Hallucination Detection for Multimodal Large Language Models](https://mlsanity.com/paper/2402.03190/) (2024)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks](https://mlsanity.com/paper/2407.21059/) (2024)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)
- [LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation](https://mlsanity.com/paper/2401.17244/) (2024)
- [Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems](https://mlsanity.com/paper/2405.20774/) (2024)
- [SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions](https://mlsanity.com/paper/2407.11417/) (2024)
- [KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking](https://mlsanity.com/paper/2404.02935/) (2024)
- [Prompting open-source and commercial language models for grammatical error correction of English learner text](https://mlsanity.com/paper/2401.07702/) (2024)
- [Jill Watson: A Virtual Teaching Assistant powered by ChatGPT](https://mlsanity.com/paper/2405.11070/) (2024)
- [DataGen: Unified Synthetic Dataset Generation via Large Language Models](https://mlsanity.com/paper/2406.18966/) (2024)
- [Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors](https://mlsanity.com/paper/2411.01705/) (2024)
- [Enhancing Retrieval-Augmented Generation: A Study of Best Practices](https://mlsanity.com/paper/2501.07391/) (2025)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations](https://mlsanity.com/paper/2410.04241/) (2024)
- [Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval](https://mlsanity.com/paper/2407.03585/) (2024)
- [ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models](https://mlsanity.com/paper/2407.04693/) (2024)
- [COVE: COntext and VEracity prediction for out-of-context images](https://mlsanity.com/paper/2502.01194/) (2025)
- [SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models](https://mlsanity.com/paper/2311.09818/) (2023)
- [Web Retrieval Agents for Evidence-Based Misinformation Detection](https://mlsanity.com/paper/2409.00009/) (2024)
- [SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing](https://mlsanity.com/paper/2406.00562/) (2024)
- [Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.02835/) (2025)
- [Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning](https://mlsanity.com/paper/2406.05064/) (2024)
- [ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions](https://mlsanity.com/paper/2407.00942/) (2024)
- [Panacea: A foundation model for clinical trial search, summarization, design, and recruitment](https://mlsanity.com/paper/2407.11007/) (2024)

## 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.