Researchers have introduced CALICO, a novel system designed to improve the process of codebook-based annotation for large language models. CALICO treats prompts as editable and optimizable artifacts, allowing domain experts to better understand and correct model behavior. The system integrates various optimization techniques, including a new reflection-based optimizer called ReflectAgent, and has demonstrated significant improvements in annotation performance across different coders. AI
IMPACT Enhances the reliability and auditability of LLM-based annotation, potentially improving the quality of AI models trained on such data.
RANK_REASON The item describes a new system and methodology for annotation presented in a research paper on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
