arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.01609cs.AI
收藏

结构分解用于LLM推理:跨领域验证与语义网集成

Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration

Warsaw University of Technology(华沙技术大学)

Albert Sadowski, Jarosław A. Chudziak

AI总结:

本文提出结构分解框架,结合LLM与符号推理,通过本体填充和符号验证提升跨领域推理的准确性和一致性。

摘要:

基于规则的自然语言输入推理出现在需要可审计和可辩护的决策领域:临床协议用散文指定资格标准,证据规则通过文本条件定义可接受性,科学标准规定方法学要求。对这类输入应用规则需要既具解释灵活性又具形式保证。大型语言模型(LLMs)提供灵活性但无法确保一致的规则应用;符号系统提供保证但需要结构化输入。本文提出一种整合模式,结合这些优势:LLMs充当本体填充引擎,根据专家编写的TBox规范将非结构化文本转换为ABox断言,而基于SWRL的推理器则能以确定性保证应用规则。该框架将推理分解为实体识别、断言提取和符号验证,任务定义基于OWL 2本体。在三个领域(法律传闻判定、科学方法-任务应用、临床试验资格)和十一种语言模型上的实验验证了该方法。结构分解在汇总上比少样本提示法有统计学显著改进,在所有三个领域均观察到收益。消融研究证实,符号验证在结构化提示之外提供了实质性的好处。填充的ABox可与标准语义网工具进行检查和查询,使该框架能够实现更丰富的推理模式,而更简单的形式化方法无法表达。

英文摘要:

Rule-based reasoning over natural language input arises in domains where decisions must be auditable and justifiable: clinical protocols specify eligibility criteria in prose, evidence rules define admissibility through textual conditions, and scientific standards dictate methodological requirements. Applying rules to such inputs demands both interpretive flexibility and formal guarantees. Large language models (LLMs) provide flexibility but cannot ensure consistent rule application; symbolic systems provide guarantees but require structured input. This paper presents an integration pattern that combines these strengths: LLMs serve as ontology population engines, translating unstructured text into ABox assertions according to expert-authored TBox specifications, while SWRL-based reasoners apply rules with deterministic guarantees. The framework decomposes reasoning into entity identification, assertion extraction, and symbolic verification, with task definitions grounded in OWL 2 ontologies. Experiments across three domains (legal hearsay determination, scientific method-task application, clinical trial eligibility) and eleven language models validate the approach. Structured decomposition achieves statistically significant improvements over few-shot prompting in aggregate, with gains observed across all three domains. An ablation study confirms that symbolic verification provides substantial benefit beyond structured prompting alone. The populated ABox integrates with standard semantic web tooling for inspection and querying, positioning the framework for richer inference patterns that simpler formalisms cannot express.

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。

↑