Evidence Alignment and Transfer Boundaries in Llm Extraction Defense And Structured Knowledge Extraction

Abstract

Research spanning LLM extraction defense and structured knowledge extraction increasingly joins methods that were developed for different objects and decisions. Here, a honeypot knowledge graph that redirects model-extraction queries toward low-transferability knowledge is compared with large-language-model generation and labeling of molecular concepts to determine which claims can travel across those boundaries and which remain context dependent. A structured reading of two target studies and 12 verified companion references is conducted across five lenses: attack modeling, honeypot knowledge, query economics, utility preservation, adaptive attackers. Emphasis is placed on the provenance of evidence, the comparability of baselines, and the consequences of alternative explanations. Comparison reveals recurring trade-offs among attack modeling, honeypot knowledge, and query economics. These trade-offs do not support a universal ranking; instead, they identify the operating envelope within which each method remains credible and the perturbations most likely to expose fragile conclusions. The article concludes with a research agenda built around transparent comparators, targeted stress tests, and evidence records that can be reused without overstating causal or practical reach.