DALM：通过三阶段结构生成的领域代数语言模型
DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation
AI总结：
DALM通过三阶段结构生成框架，利用领域格子进行约束生成，解决领域不确定性、关系不确定性和概念不确定性，实现跨领域污染控制和多视角回答空间生成。
摘要：
大型语言模型将异质知识压缩到单一参数空间，允许不同领域事实在生成过程中相互干扰。我们提出了DALM，一种领域代数语言模型，通过领域格子上的结构去噪替代无约束的token生成。DALM遵循三阶段生成路径：首先解决领域不确定性，然后关系不确定性，最后概念不确定性，每个阶段均在显式代数约束下操作。该框架仅需三个要素：具有可计算meet、join和implication的领域格子；控制跨领域继承的类型函数；以及局部化知识到领域特定子集的纤维划分。给定这些要素，DALM产生一个三阶段编码器-解码器架构，在领域纤维内限制生成，封闭词汇模式下结构上防止跨领域污染，在开放词汇模式下可审计地限制污染，并且单个查询可生成领域索引的多视角回答空间。我们用CDC知识表示系统实例化该框架，并概述在经过验证的领域注释晶体库上的训练和评估。DALM将语言生成重新定义为代数约束下的结构去噪，而非在平坦token空间上的无约束解码。
英文摘要：
Large language models compress heterogeneous knowledge into a single parameter space, allowing facts from different domains to interfere during generation. We propose DALM, a Domain-Algebraic Language Model that replaces unconstrained token generation with structured denoising over a domain lattice. DALM follows a three-phase generation path: it first resolves domain uncertainty, then relation uncertainty, and finally concept uncertainty, so each stage operates under explicit algebraic constraints. The framework requires only three ingredients: a lattice of domains with computable meet, join, and implication; a typing function over relations that controls inheritance across domains; and a fiber partition that localizes knowledge to domain-specific subsets. Given these ingredients, DALM yields a three-phase encoder-decoder architecture in which generation is confined to a domain fiber, cross-domain contamination is structurally prevented in closed-vocabulary mode and auditably bounded in open-vocabulary mode, and a single query can produce a domain-indexed multi-perspective answer space. We instantiate the framework with the CDC knowledge representation system and outline training and evaluation on validated domain-annotated crystal libraries. DALM reframes language generation as algebraically constrained structured denoising rather than unconstrained decoding over a flat token space.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
