Matches in Nanopublications for { <https://neverblink.eu/ontologies/llm-kg/methods#iracKgAssistedLlmPostTraining> ?p ?o ?g. }
Showing items 1 to 5 of
5
with 100 items per page.
- iracKgAssistedLlmPostTraining type Workflow assertion.
- iracKgAssistedLlmPostTraining label "IRAC KG-Assisted LLM Post-Training" assertion.
- iracKgAssistedLlmPostTraining comment "This method proposes a comprehensive approach where a specialized IRAC (Issue, Rule, Analysis, Conclusion) Knowledge Graph is constructed and subsequently used to generate high-quality training data. This data is then employed for post-training (via Supervised Fine-Tuning and Direct Preference Optimization) of Large Language Models, thereby enhancing their intrinsic legal reasoning capabilities and knowledge expression. While it's 'post-training' rather than initial 'pre-training', the core mechanism involves fundamentally improving the LLM's internal knowledge through a structured training process, aligning with the goal of enhancing LLM knowledge expression in a training stage." assertion.
- iracKgAssistedLlmPostTraining subject KGEnhancedLLMPretraining assertion.
- iracKgAssistedLlmPostTraining hasTopCategory KGEnhancedLLM assertion.