实时逐字验证修正大模型输出，提升准确率与效率
Efficient Real-time Refinement of Language Model Text Generation
- 生成过程中即时验证并修正每段文本，避免错误累积
- 在多个数据集上显著提升事实准确性，速度优于传统方法
- 适合对生成质量要求高、需低延迟的应用场景
大语言模型在多种自然语言任务中表现卓越，但常产生事实性错误。现有方法通常在生成完整文本后才进行验证与修正，效率低下。我们观察到早期错误会增加后续错误概率。为此，提出 Streaming-VR（流式验证与修正），可在生成过程中实时逐段验证并修正输出，利用另一大模型对每部分文本即时检查和优化。在多个数据集上的实验表明，该方法不仅显著提升事实准确性，还比以往修正方法更高效。
原文摘要 · Abstract (English)
Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many previous work has focused on identifying errors in their generation and further refining them, they are slow in deployment since they are designed to verify the response from LLMs only after their entire generation (from the first to last tokens) is done. Further, we observe that once LLMs generate incorrect tokens early on, there is a higher likelihood that subsequent tokens will also be factually incorrect. To this end, in this work, we propose Streaming-VR (Streaming Verification and Refinement), a novel approach designed to enhance the efficiency of verification and refinement of LLM outputs. Specifically, the proposed Streaming-VR enables on-the-fly verification and correction of tokens as they are being generated, similar to a streaming process, ensuring that each subset of tokens is checked and refined in real-time by another LLM as the LLM constructs its response. Through comprehensive evaluations on multiple datasets, we demonstrate that our approach not only enhances the factual accuracy of LLMs, but also offers a more efficient solution compared to prior refinement methods.
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。