Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RArK6wV1lccoEjvnpW90mGbdcgqRslzKtl7USDyogx1KQ/assertion>. }
Showing items 1 to 23 of
23
with 100 items per page.
- graphRAG type Workflow assertion.
- arXiv.2601.13806 type Entity assertion.
- directPreferenceOptimization type Workflow assertion.
- graphOfThoughts type Workflow assertion.
- iracKgAssistedLlmPostTraining type Workflow assertion.
- supervisedFineTuning type Workflow assertion.
- treeOfThoughts type Workflow assertion.
- graphRAG label "GraphRAG" assertion.
- directPreferenceOptimization label "Direct Preference Optimization" assertion.
- graphOfThoughts label "Graph-of-Thoughts" assertion.
- iracKgAssistedLlmPostTraining label "IRAC KG-Assisted LLM Post-Training" assertion.
- supervisedFineTuning label "Supervised Fine-Tuning" assertion.
- treeOfThoughts label "Tree-of-Thoughts" 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.
- arXiv.2601.13806 describes iracKgAssistedLlmPostTraining assertion.
- arXiv.2601.13806 discusses graphRAG assertion.
- arXiv.2601.13806 discusses directPreferenceOptimization assertion.
- arXiv.2601.13806 discusses graphOfThoughts assertion.
- arXiv.2601.13806 discusses supervisedFineTuning assertion.
- arXiv.2601.13806 discusses treeOfThoughts assertion.
- iracKgAssistedLlmPostTraining subject KGEnhancedLLMPretraining assertion.
- arXiv.2601.13806 title "Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning" assertion.
- iracKgAssistedLlmPostTraining hasTopCategory KGEnhancedLLM assertion.