SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation
This provides a granular evaluation method for researchers to better understand and enhance LLM capabilities, though it is incremental as it builds on existing evaluation techniques.
The paper tackles the problem of evaluating language models on complex tasks by introducing SkillVerse, an unsupervised tree-structured diagnosis framework that assesses model proficiency in specific abilities, resulting in a 25% improvement in in-context learning and a 55% success rate in predicting model weaknesses.
As language models evolve to tackle complex, multifaceted tasks, their evaluation must adapt to capture this intricacy. A granular, skill-specific understanding of model capabilities can empower researchers to make informed model development plans. In this paper, we introduce SkillVerse, an unsupervised tree-structured diagnosis framework for understanding model proficiency in specific abilities. With LLM as a judge, SkillVerse first critiques the model responses, and then organizes them into a hierarchical structure termed dendrogram. Given proficiency at arbitrary levels of granularity, SkillVerse is flexible to produce insights of behaviors of modern large models. We also demonstrate its efficacy in two downstream tasks: 1) improving model in-context learning by 25% using a tree-search algorithm to select more informative few-shot demonstrations, and 2) accurately predicting new model weaknesses with a 55% success rate, 22% higher than without SkillVerse.