Tag
该论文系统比较了LLM生成的知识引导在知识型VQA中的两种集成策略，发现浅层的决策级晚期融合（39.4% EM）在数据稀缺场景下优于深层的注意力注入（31.8%），并提出了一种基于LLM的数据增强管线，将训练数据扩充十倍以上。
MedKIT is a new benchmark evaluating how well LLMs integrate and apply updated clinical knowledge across lexical, relational, compositional, and operational probes. A large-scale study of 12 knowledge integration strategies across 5 models reveals a persistent gap between factual recall and usable knowledge, with little improvement on compositional or operational reasoning.
Knowledge Pull Requests (KPRs) is a framework for continual document authoring that integrates new knowledge by extracting claims, filtering them, and producing a ChangeLog to make changes interpretable. It outperforms existing methods in preserving content and adding information, as evaluated on Wikipedia revisions and RAGTIME tasks.
This survey paper defines model fusion and organizes research into three levels—parameter, representation, and behavior—for integrating capabilities in large language models.
iFuzz-Meta is an interpretable fuzzy learning framework that combines top-down knowledge integration with bottom-up data-driven adaptation to enhance transparency and generalization in neural models.