Pinned Loading
-
classify_hateXplain_llm
classify_hateXplain_llm PublicLLM annotation of hate speech on HateXplain (GPT-5-mini, zero/few-shot), agreement with human labels, and target-swap adversarial tests with Claude
Python
-
Ember
Ember PublicEMBER: RAG-based corrective action recommendation for HIPAA breaches (hybrid BM25 + dense retrieval, GPT-4o, BERTScore evaluation)
Python
-
-
AI-Development-Assistant
AI-Development-Assistant PublicAgentic SDLC coding platform: LangGraph-style workflows, Gemini tool calling, Neo4j vector search and sandboxed code execution (Java, Spring Boot, React)
Java
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.