Matches in Nanopublications for { <https://neverblink.eu/ontologies/llm-kg/methods#LLMAtKGE> ?p ?o ?g. }
Showing items 1 to 6 of
6
with 100 items per page.
- LLMAtKGE type Workflow assertion.
- LLMAtKGE label "LLMAtKGE" assertion.
- LLMAtKGE comment "LLMAtKGE is a unified framework leveraging LLMs to perform explainable adversarial attacks on KGEs. A core component, "High-order Adjacency Tuning LLM for Filtering," precomputes multi-hop KG structural information and transforms it into the LLM's embedding space via a dedicated adapter. This adapter, jointly trained with the LLM using LoRA on a triple classification task, acts as a KG fusion module that effectively represents knowledge from both sources, thus fitting the SynergizedKnowledgeRepresentation category." assertion.
- LLMAtKGE subject SynergizedKnowledgeRepresentation assertion.
- LLMAtKGE hasURL "https://github.com/liting1024/LLMAtKGE" assertion.
- LLMAtKGE hasTopCategory SynergizedLLMKG assertion.