Mothman at SemEval-2024 Process 9: An Iterative System for Chain-of-Thought Immediate Optimization
Authors: Alvin Po-Chun Chen, Ray Groshan, Sean von Bayern
Summary: Intensive analysis exists on the efficiency of huge language fashions on logic-based duties, whereas comparatively little has been completed on their potential to generate artistic options on lateral pondering duties. The BrainTeaser shared activity assessments lateral pondering and makes use of adversarial datasets to forestall memorization, leading to poor efficiency for out-of-the-box fashions. We suggest a system for iterative, chain-of-thought immediate engineering which optimizes prompts utilizing human analysis. Utilizing this shared activity, we exhibit our system’s potential to considerably enhance mannequin efficiency by optimizing prompts and consider the enter dataset
