paper-with-me

Papers

HiBug: On Human-Interpretable Model Debug

2023-09-21 · NeurIPS 2023 11

Machine learning models can frequently produce systematic errors on critical subsets (or slices) of data that share common attributes. Discovering and explaining such model bugs is crucial for reliable model deployment. However, existing bug discovery and interpretation methods usually involve heavy human intervention and annotation, which can be cumbersome and have low bug coverage. In this paper, we propose HiBug, an automated framework for interpretable model debugging. Our approach utilizes large pre-trained models, such as chatGPT, to suggest human-understandable attributes that are related to the targeted computer vision tasks. By leveraging pre-trained vision-language models, we can efficiently identify common visual attributes of underperforming data slices using human-understandable terms. This enables us to uncover rare cases in the training data, identify spurious correlations in the model, and use the interpretable debug results to select or generate new training data for model improvement. Experimental results demonstrate the efficacy of the HiBug framework.

📄 PDF Abstract BibTeX

Code (1)

cure-lab/hibug 공식 구현 pytorch

Similar Papers 제목 키워드 기반

NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations

2023-10-11 · Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee

Despite deep learning (DL) has achieved remarkable progress in various domains, the DL models are still prone to making mistakes. This issue necessitates effective debugging tools for DL practitioners to interpret the de…

counterfactualDecision MakingImage Classification

Debugging Concept Bottleneck Models through Removal and Retraining

2025-09-23 · Eric Enouen, Sainyam Galhotra arxiv

Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label, enabling domain experts to not only validate the CBM's predictions, but also intervene on incorrect concepts at …

Intermediate Entity-based Sparse Interpretable Representation Learning

2022-12-03 · Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh, Byron C. Wallace

Interpretable entity representations (IERs) are sparse embeddings that are "human-readable" in that dimensions correspond to fine-grained entity types and values are predicted probabilities that a given entity is of the …

counterfactualRepresentation Learning

DebugAgent: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

2025-01-28 · Muxi Chen, Chenchen Zhao, Qiang Xu

Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices. Identifying and mitigating these error slices is crucial…

image-classificationImage Classificationobject-detectionObject Detection+2

Data Science with LLMs and Interpretable Models

2024-02-22 · Sebastian Bordt, Ben Lengerich, Harsha Nori, Rich Caruana

Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we show that large language models (LLMs) are …

Additive modelsQuestion Answering