Picture for Tsui-Wei Weng

Tsui-Wei Weng

Statistical Inference for Responsiveness Verification

Add code
Jul 02, 2025
Viaarxiv icon

Rethinking Crowd-Sourced Evaluation of Neuron Explanations

Add code
Jun 09, 2025
Viaarxiv icon

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks

Add code
Jun 06, 2025
Viaarxiv icon

Effective Skill Unlearning through Intervention and Abstention

Add code
Mar 27, 2025
Viaarxiv icon

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models

Add code
Mar 27, 2025
Viaarxiv icon

Interpretable Generative Models through Post-hoc Concept Bottlenecks

Add code
Mar 25, 2025
Viaarxiv icon

RAT: Boosting Misclassification Detection Ability without Extra Data

Add code
Mar 18, 2025
Viaarxiv icon

Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data

Add code
Feb 27, 2025
Viaarxiv icon

Understanding Fixed Predictions via Confined Regions

Add code
Feb 22, 2025
Viaarxiv icon

Concept Bottleneck Large Language Models

Add code
Dec 11, 2024
Figure 1 for Concept Bottleneck Large Language Models
Figure 2 for Concept Bottleneck Large Language Models
Figure 3 for Concept Bottleneck Large Language Models
Figure 4 for Concept Bottleneck Large Language Models
Viaarxiv icon