2021/10/22 by Thang M. Pham, Pham, Thang M., Trung Bui +5
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2110.11929
openalex publication_date 2021/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A principle behind dozens of attribution methods is to take the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. A popular Input Marginalization (IM) method (Kim et al., 2020) uses BERT to replace a token, yielding more plausible counterfactuals. While Kim et al. (2020) reported that IM is effective, we find this conclusion not convincing as the DeletionBERT metric used in their paper is biased towards IM. Importantly, this bias exists in Deletion-based metrics, including Insertion, Sufficiency, and Comprehensiveness. Furthermore, our rigorous evaluation using 6 metrics and 3 datasets finds no evidence that IM is better than a Leave-One-Out (LOO) baseline. We find two reasons why IM is not better than LOO: (1) deleting a single word from the input only marginally reduces a classifier's accuracy; and (2) a highly predictable word is always given near-zero attribution, regardless of its true importance to the classifier. In contrast, making LIME samples more natural via BERT consistently improves LIME accuracy under several ROAR metrics.