摘要：概率式问答系统——无论是大语言模型（LLM）本身、检索增强生成（RAG），还是经过训练的多跳检索器——都会将“已知什么”和“如何推理”混合为一次统一的概率计算：幻觉无法被根除，证据链无法被审计，且系统即使在不知道答案时仍会作答。我们提出 LatWeave：该系统将知识组织为多维知识格，并将多跳问答编译为三种确定性算子——相交（约束交集）、比较（格序比较）和弃答（结构化弃答）；LLM 仅出现在构建侧（一次性抽取）和查询规划侧，而答案生成路径不使用 LLM、无需任务训练，并且可端到端审计——因此，针对 Web 发布知识的问答能够逐项复现。我们并不宣称在所有场景中达到 SOTA，而是在六个公开基准上刻画这一范式的适用范围：当知识完整时（MetaQA，39,093 个问题），相交链在三跳内几乎无损（任一命中率 0.9975，与完全监督的 KBQA 相当）；在模板化多跳的主场景中（2WikiMultihopQA 留出集，n=1,258），EM 为 0.865，显著高于已发表的结构增强型 RAG 复现结果；在开放文本深度组合场景（MuSiQue）及抽取覆盖缺口场景（HotpotQA）中，我们如实报告了性能下降，并将其归因于知识格代数层之外的原因；当信息不完整时（IIRC），我们实现了结构化弃答，弃答准确率为 0.971，泄漏率为 0.029。在这一适用范围内，确定性执行不需要付出性能代价，并且答案路径上的每一步都可以重新计算——这正是端到端可审计性的来源。

Abstract:Probabilistic question-answering systems -- whether large language models (LLMs) themselves, retrieval-augmented generation (RAG), or trained multi-hop retrievers -- conflate "what is known" and "how to reason" into a single probabilistic computation: hallucination cannot be eradicated, evidence chains cannot be audited, and the system answers even when it does not know. We present LatWeave, which organizes knowledge into a multidimensional knowledge lattice and compiles multi-hop QA into three deterministic operators -- meet (constraint intersection), compare (lattice-order comparison), and abstain (structural abstention); LLMs appear only on the construction side (one-shot extraction) and the query-planning side, while the answer-generation path is zero-LLM, zero-task-training, and auditable end to end -- so that question answering over Web-published knowledge becomes reproducible item by item. Rather than claiming across-the-board SOTA, we characterize the operating envelope of this paradigm on six public benchmarks: when knowledge is complete (MetaQA, 39,093 questions) meet chains are near-lossless over three hops (any-hit 0.9975, on par with fully supervised KBQA); on templated multi-hop home ground (2WikiMultihopQA held-out n=1,258) EM 0.865, well above published structure-augmented RAG reproductions; on open-text deep composition (MuSiQue) and extraction-coverage gaps (HotpotQA) we report degradation honestly and attribute it to causes outside the lattice-algebra layer; and when information is incomplete (IIRC) we achieve structural abstention with abstain accuracy 0.971 and leak rate 0.029. Within the operating envelope, deterministic execution pays no performance penalty, and every step on the answer path can be recomputed -- precisely the source of end-to-end auditability.