WikiChat：通过基于Wikipedia的少样本接地抑制大语言模型聊天机器人的幻觉
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
AI总结：
本研究提出基于Wikipedia少样本接地的聊天机器人WikiChat，通过保留生成内容中接地事实并结合检索信息抑制幻觉，蒸馏为7B参数LLaMA模型后仍实现高事实准确率，在多类知识任务上显著优于GPT-4等基线。
摘要：
本文提出了首个基于大语言模型（LLM）的少样本聊天机器人WikiChat，它几乎不会产生幻觉，同时具备高对话性与低延迟的特点。该模型以英文Wikipedia——最大的经整理的自由文本语料库——作为知识接地依据。\nWikiChat先由LLM生成回复，仅保留其中有依据的事实，再将其与从语料库中检索到的补充信息相结合，形成既符合事实又具有吸引力的回复。我们将基于GPT-4的WikiChat蒸馏为一个70亿参数的LLaMA模型，在质量损失极小的前提下，显著提升了延迟、成本与隐私性表现，也为后续研究和部署提供了便利。\n通过一种新颖的人工与LLM混合评估方法，我们证明最优系统在模拟对话中达到97.3%的事实准确率，显著优于所有基于检索和基于LLM的基线模型；在头部知识、尾部知识和近期知识上，分别比GPT-4高出3.9%、38.6%和51.0%。与此前最先进的基于检索的聊天机器人相比，WikiChat的信息丰富度和吸引力也显著更高，表现与LLM相当。\n在与人类用户围绕近期主题展开的对话中，WikiChat的事实准确率达到97.9%，比GPT-4高55.0%，同时获得了显著更高的用户评分和更多正面评价。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
