让大模型生成时自带可实时纠错的记忆，提升长文本事实准确性。
Improving Factuality with Explicit Working Memory
- 引入显式工作记忆，结合外部反馈动态更新信息
- 在4个数据集上使事实性得分提升2至6点
- 适合需要高准确性的长文本生成场景
大型语言模型常产生事实错误，即幻觉问题。现有基于检索增强生成的方法虽通过迭代提示改善事实性，但受限于传统RAG架构。为此，我们提出EWE（显式工作记忆），一种通过集成可接收外部资源实时反馈的工作记忆来提升长文本生成事实性的新方法。该记忆模块基于在线事实核查和检索反馈进行刷新，可在生成过程中修正错误陈述，确保输出更准确可靠。实验表明，EWE在四个事实导向的长文本生成数据集上优于强基线，使事实性指标VeriScore绝对提升2至6点，且不牺牲回答有用性。进一步分析显示，记忆更新规则设计、记忆单元配置及检索数据存储质量是影响模型性能的关键因素。
原文摘要 · Abstract (English)
Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 6 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.
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。