通过重构查询与上下文，实现GPT-4和GPT-3.5 Turbo零幻觉生成。
100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
- 重构输入查询与上下文格式，提升模型对事实的忠实度。
- 在RAGTruth数据集上对GPT-4和GPT-3.5 Turbo实现100%无幻觉。
- 适合追求高可信度AI输出的企业级应用开发者。
大语言模型（LLM）中的幻觉问题仍是AI在企业及高风险场景中应用的主要障碍。尽管检索增强生成（RAG）系统有所进展，现有最先进方法在提供相关准确上下文时，仍无法实现超过80%的生成准确性。本文提出Acurai，一种系统性方法，通过在输入前重构查询与上下文数据，使GPT-4和GPT-3.5 Turbo实现100%无幻觉输出。该方法基于对LLM内部表征、名词短语主导性及离散功能单元（DFUs）作用的深入理解，确保输入上下文与生成结果的一致性。在RAGTruth数据集上的验证表明，该方法可彻底消除两类模型的幻觉，为可信AI系统的发展树立新标准。
原文摘要 · Abstract (English)
The issue of hallucinations in large language models (LLMs) remains a critical barrier to the adoption of AI in enterprise and other high-stakes applications. Despite advancements in retrieval-augmented generation (RAG) systems, current state-of-the-art methods fail to achieve more than 80% accuracy in generating faithful and factually correct outputs, even when provided with relevant and accurate context. In this work, we introduce Acurai, a novel systematic approach that achieves 100% hallucination-free responses in LLMs by reformatting queries and context data prior to input. Leveraging a deep understanding of LLM internal representations, the importance of noun-phrase dominance, and the role of discrete functional units (DFUs), Acurai ensures alignment between input context and generated output. We validate this method using the RAGTruth corpus, demonstrating its ability to eliminate 100% hallucinations for both GPT-4 and GPT-3.5 Turbo. Acurai sets a new standard for achieving consistent, accurate, and faithful AI responses, marking a significant step forward in the development of trustworthy AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。