GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics

Recent advances in measuring hardness-wise properties of data guide language models in sample selection within low-resource scenarios. However, class-specific properties are overlooked for task setup and learning. How will these properties influence model learning and is it generalizable across datasets? To answer this question, this work formally initiates the concept of class-wise hardness. Experiments across eight natural language understanding (NLU) datasets demonstrate a consistent hardness distribution across learning paradigms, models, and human judgment. Subsequent experiments unveil a notable challenge in measuring such class-wise hardness with instancelevel metrics in previous works. To address this, we propose GeoHard for class-wise hardness measurement by modeling class geometry in the semantic embedding space. GeoHard surpasses instance-level metrics by over 59 percent on Pearson's correlation on measuring classwise hardness. Our analysis theoretically and empirically underscores the generality of Geo-Hard as a fresh perspective on data diagnosis. Additionally, we showcase how understanding class-wise hardness can practically aid in improving task learning. The code for GeoHard is available 1 .