Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RAe5-l8XUIWC0J0kshCll4i11gVSeDXeeCpMnD_bZZ13s/assertion>. }
Showing items 1 to 29 of
29
with 100 items per page.
- arXiv.2511.07480 type Entity assertion.
- Gcg type Workflow assertion.
- KgDf type Workflow assertion.
- Pair type Workflow assertion.
- Ppl type Workflow assertion.
- Rpo type Workflow assertion.
- SelfReminder type Workflow assertion.
- SmoothLlm type Workflow assertion.
- Tap type Workflow assertion.
- Gcg label "GCG" assertion.
- KgDf label "KG-DF" assertion.
- Pair label "PAIR" assertion.
- Ppl label "PPL" assertion.
- Rpo label "RPO" assertion.
- SelfReminder label "Self-reminder" assertion.
- SmoothLlm label "SmoothLLM" assertion.
- Tap label "TAP" assertion.
- KgDf comment "KG-DF is a unified framework where a Knowledge Graph (KG) is constructed with safety and general knowledge. An LLM performs semantic parsing of user input to extract keywords, which are then used to retrieve relevant KG triples. These triples are integrated into the LLM's prompt as a "warning" and the LLM then performs a judgment (reasoning) to decide whether to respond or reject, thereby enhancing LLM security against jailbreak attacks and improving general QA. This constitutes a synergistic reasoning process where the LLM acts as an agent interacting with KG-derived knowledge for decision-making." assertion.
- arXiv.2511.07480 describes KgDf assertion.
- arXiv.2511.07480 discusses Gcg assertion.
- arXiv.2511.07480 discusses Pair assertion.
- arXiv.2511.07480 discusses Ppl assertion.
- arXiv.2511.07480 discusses Rpo assertion.
- arXiv.2511.07480 discusses SelfReminder assertion.
- arXiv.2511.07480 discusses SmoothLlm assertion.
- arXiv.2511.07480 discusses Tap assertion.
- KgDf subject SynergizedReasoning assertion.
- arXiv.2511.07480 title "KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs" assertion.
- KgDf hasTopCategory SynergizedLLMKG assertion.