A team is developing a system that iteratively refines a complex legal document summary. The system reads its current summary, identifies areas for improvement, and generates a new version. To manage computational costs, the team decides the system will always stop after exactly 5 refinement cycles, regardless of the summary's quality. What is the most significant potential drawback of this specific stopping criterion?
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Evaluation in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A team is developing a system that iteratively refines a complex legal document summary. The system reads its current summary, identifies areas for improvement, and generates a new version. To manage computational costs, the team decides the system will always stop after exactly 5 refinement cycles, regardless of the summary's quality. What is the most significant potential drawback of this specific stopping criterion?
Evaluating Stopping Criteria for AI Text Generation
In an iterative process designed to improve the clarity of a technical explanation, a stopping criterion based solely on the output's similarity score to the previous version is sufficient to guarantee an optimal result.