Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RA1zdDEkG1IMROFHn5QJzBxB2ipl07uoHb6LLmWJ_YHeU/assertion>. }
Showing items 1 to 47 of
47
with 100 items per page.
- ChainOfThought type Workflow assertion.
- TreeOfThought type Workflow assertion.
- GraphRAG type Workflow assertion.
- BERT type Workflow assertion.
- arXiv.2412.15268 type Entity assertion.
- EmbeddingBasedMethods type Workflow assertion.
- HateBERT type Workflow assertion.
- LLMsAsDataAugmentationTools type Workflow assertion.
- MetaTox type Workflow assertion.
- NaiveRetrievalAugmentedGeneration type Workflow assertion.
- RuleBasedMethods type Workflow assertion.
- STaR type Workflow assertion.
- TextAttack type Workflow assertion.
- ToxicTrapModular type Workflow assertion.
- TransformerBasedMethods type Workflow assertion.
- ChainOfThought label "Chain-of-Thought (CoT)" assertion.
- TreeOfThought label "Tree-of-Thought (ToT)" assertion.
- GraphRAG label "GraphRAG" assertion.
- BERT label "BERT" assertion.
- EmbeddingBasedMethods label "Embedding-based methods" assertion.
- HateBERT label "HateBERT" assertion.
- LLMsAsDataAugmentationTools label "LLMs as data augmentation tools" assertion.
- MetaTox label "Meta-Tox" assertion.
- NaiveRetrievalAugmentedGeneration label "Naive Retrieval Augmented Generation" assertion.
- RuleBasedMethods label "Rule-based methods" assertion.
- STaR label "STaR" assertion.
- TextAttack label "TextAttack" assertion.
- ToxicTrapModular label "ToxicTrap modular" assertion.
- TransformerBasedMethods label "Transformer-based methods" assertion.
- MetaTox comment "Meta-Tox is a novel method that first utilizes LLMs to construct a meta-toxic knowledge graph through a three-step pipeline (rationale reasoning, triplet extraction, and entity resolution). Subsequently, it queries this graph via retrieval and ranking to supplement accurate, relevant toxicity knowledge. This knowledge is then used to prompt LLMs, boosting their capability in hatred and toxicity detection during inference, thus demonstrating a unified framework where LLMs act as agents both in building and interacting with the KG for reasoning." assertion.
- arXiv.2412.15268 describes MetaTox assertion.
- arXiv.2412.15268 discusses ChainOfThought assertion.
- arXiv.2412.15268 discusses TreeOfThought assertion.
- arXiv.2412.15268 discusses GraphRAG assertion.
- arXiv.2412.15268 discusses BERT assertion.
- arXiv.2412.15268 discusses EmbeddingBasedMethods assertion.
- arXiv.2412.15268 discusses HateBERT assertion.
- arXiv.2412.15268 discusses LLMsAsDataAugmentationTools assertion.
- arXiv.2412.15268 discusses NaiveRetrievalAugmentedGeneration assertion.
- arXiv.2412.15268 discusses RuleBasedMethods assertion.
- arXiv.2412.15268 discusses STaR assertion.
- arXiv.2412.15268 discusses TextAttack assertion.
- arXiv.2412.15268 discusses ToxicTrapModular assertion.
- arXiv.2412.15268 discusses TransformerBasedMethods assertion.
- MetaTox subject SynergizedReasoning assertion.
- arXiv.2412.15268 title "Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph" assertion.
- MetaTox hasTopCategory SynergizedLLMKG assertion.