AI 中文总结
研究针对RAG系统中因未考虑时间来源导致的时间幻觉问题，提出Chronofy三层神经符号框架，通过嵌入时间有效性到表示、检索和推理层，经实验验证该框架能提高检索精度、减少幻觉并启用数据重新获取触发机制。
AI 中文摘要
检索增强生成（RAG）系统检索并整合外部知识以支撑大语言模型（LLM）输出。然而，当前RAG架构将所有检索到的事实都视为同等有效，而不考虑时间来源，导致时间幻觉，即看似合理但过时的事实会影响输出。我们提出了Chronofy，这是一个三层神经符号框架，实现了时态逻辑衰减架构（TLDA），将时间有效性直接嵌入到RAG系统的表示、检索和推理层中。第1层在嵌套嵌入中保留一个专用的时间子空间，使事实年龄在结构上不可从表示中移除。第2层将可学习的指数衰减函数集成到基于图的检索中，衰减系数βj基于贝叶斯决策理论作为潜在过程平均回复率两倍的近似值。第3层应用信号时态逻辑（STL）鲁棒性函数来评估检索到的知识的时间有效性，而不是LLM输出置信度，并实施可能性最弱链接原则，以推理链中最衰减的证据来限制输出置信度。我们在时间知识图预测基准、TimE时间问答基准和特定领域敏感性分析上对Chronofy进行了评估，结果表明显式时间衰减建模提高了检索精度，减少了时间幻觉，并在时间上下文不足时启用了有原则的数据重新获取触发机制。
英文摘要
Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make fact age structurally irremovable from the representation. Layer 2 integrates learnable exponential decay functions into graph-based retrieval, where the decay coefficient $β_j$ is grounded in Bayesian decision theory as an approximation of twice the latent process mean-reversion rate. Layer 3 applies Signal Temporal Logic (STL) robustness functions to evaluate the temporal validity of retrieved knowledge, not LLM output confidence, and enforces the possibilistic weakest-link principle to bound output confidence by the most decayed evidence in the reasoning chain. We evaluate Chronofy on temporal knowledge graph forecasting benchmarks, the TimE temporal QA benchmark, and a domain-specific sensitivity analysis, demonstrating that explicit temporal decay modeling improves retrieval precision, reduces temporal hallucination, and enables principled data re-acquisition triggers when temporal context is insufficient.
