mlchrzan/pairadigm
Concept-Guided Chain-of-Thought (CGCoT) pairwise annotation tool for systematic text evaluation using LLMs. Generate breakdowns, compare items, compute scores, and validate against human judgments. Supports Ollama, Hugging Face, Google Gemini, OpenAI, and Anthropic models.
GitHub repository with 9 stars and 0 forks.
Language: Jupyter Notebook
Topics: alt-test, annotation, bradley-terry, chain-of-thought, data-science, human-evaluation, llm, machine-learning, nlp, pairwise-comparison