QualEval: Qualitative Evaluation for Model Improvement

arXiv:2311.02807v2 Announce Type: replace
Abstract: Quantitative evaluation metrics have traditionally been pivotal in gauging the advancements of artificial intelligence systems, including large language models (LLMs). However, these metrics have inherent limitations. Given the intricate nature of real-world tasks, a single scalar to quantify and compare is insufficient to capture the fine-grained nuances of model behavior. Metrics serve only as a way to compare and benchmark models, and do not yield actionable diagnostics, thus making the model improvement process challenging. Model …

abstract artificial artificial intelligence arxiv cs.ai cs.cl cs.lg evaluation evaluation metrics fine-grained however improvement intelligence language language models large language large language models limitations llms metrics nature pivotal quantitative systems tasks type world