Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning

no code implementations • 3 Feb 2024 • Ao Sun, Yuanyuan Yuan, Pingchuan Ma, Shuai Wang

This paper alleviates the information leakage issue by introducing label supervision in concept predication and constructing a hierarchical concept set.

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

1 code implementation • NeurIPS 2023 • Ao Sun, Pingchuan Ma, Yuanyuan Yuan, Shuai Wang

For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying important pixels, and emerging concept-based XAI explore forming explanations with concepts (e. g., a head in an image).

Instance Segmentation Semantic Segmentation

"Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process

1 code implementation • 4 May 2023 • Pingchuan Ma, Zongjie Li, Ao Sun, Shuai Wang

Moreover, we propose a novel on-the-fly (OTF) repairing scheme that repairs unethical suggestions made by LLMs in real-time.

Moral Scenarios