Anchor Points: Benchmarking Models with Much Fewer Examples

• URL: http://arxiv.org/abs/2309.08638v2
• Date: Sun, 18 Feb 2024 21:37:47 GMT
• Title: Anchor Points: Benchmarking Models with Much Fewer Examples
• Authors: Rajan Vivek, Kawin Ethayarajh, Diyi Yang, Douwe Kiela
• Abstract summary: In six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the entire dataset. Just several anchor points can be used to estimate model per-class predictions on all other points in a dataset with low mean absolute error.
• Score: 88.02417913161356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and elucidated with much smaller evaluation sets. We first show that in six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We build upon this phenomenon to propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the entire dataset. Anchor points reliably rank models: across 87 diverse language model-prompt pairs, evaluating models using 1-30 anchor points outperforms uniform sampling and other baselines at accurately ranking models. Moreover, just several anchor points can be used to estimate model per-class predictions on all other points in a dataset with low mean absolute error, sufficient for gauging where the model is likely to fail. Lastly, we present Anchor Point Maps for visualizing these insights and facilitating comparisons of the performance of different models on various regions within the dataset distribution.

Related papers

• Area under the ROC Curve has the Most Consistent Evaluation for Binary Classification [3.1850615666574806]
  This study investigates how consistent different metrics are at evaluating models across data of different prevalence. I find that evaluation metrics that are less influenced by prevalence offer more consistent evaluation of individual models and more consistent ranking of a set of models.
  arXiv  Detail & Related papers  (2024-08-19T17:52:38Z)
• A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
  We propose a two-phase (coarse-recall and fine-selection) model selection framework. It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
  arXiv  Detail & Related papers  (2024-03-28T14:44:44Z)
• Scalable Performance Analysis for Vision-Language Models [26.45624201546282]
  Joint vision-language models have shown great performance over a diverse set of tasks. Our paper introduces a more scalable solution that relies on already annotated benchmarks. We confirm previous findings that CLIP behaves like a bag of words model and performs better with nouns and verbs.
  arXiv  Detail & Related papers  (2023-05-30T06:40:08Z)
• Comparing Foundation Models using Data Kernels [13.099029073152257]
  We present a methodology for directly comparing the embedding space geometry of foundation models. Our methodology is grounded in random graph theory and enables valid hypothesis testing of embedding similarity. We show how our framework can induce a manifold of models equipped with a distance function that correlates strongly with several downstream metrics.
  arXiv  Detail & Related papers  (2023-05-09T02:01:07Z)
• Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers [66.36045164286854]
  We analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases. By choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.
  arXiv  Detail & Related papers  (2022-10-28T17:52:10Z)
• Part-Based Models Improve Adversarial Robustness [57.699029966800644]
  We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks. Our model combines a part segmentation model with a tiny classifier and is trained end-to-end to simultaneously segment objects into parts. Our experiments indicate that these models also reduce texture bias and yield better robustness against common corruptions and spurious correlations.
  arXiv  Detail & Related papers  (2022-09-15T15:41:47Z)
• On Model Calibration for Long-Tailed Object Detection and Instance Segmentation [56.82077636126353]
  We propose NorCal, Normalized for long-tailed object detection and instance segmentation. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance.
  arXiv  Detail & Related papers  (2021-07-05T17:57:20Z)
• Coarse-to-Fine Memory Matching for Joint Retrieval and Classification [0.7081604594416339]
  We present a novel end-to-end language model for joint retrieval and classification. We evaluate it on the standard blind test set of the FEVER fact verification dataset. We extend exemplar auditing to this setting for analyzing and constraining the model.
  arXiv  Detail & Related papers  (2020-11-29T05:06:03Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.