Popular repositories Loading

1. Label-free-CBM Label-free-CBM Public

   [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

   Jupyter Notebook 102 21

2. CLIP-dissect CLIP-dissect Public

   [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs

   Jupyter Notebook 50 15

3. VLG-CBM VLG-CBM Public

   [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretable concept-bottleneck-models (CBMs)

   Jupyter Notebook 17 2

4. CB-LLMs CB-LLMs Public

   [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.

   Python 13 3

5. Linear-Explanations Linear-Explanations Public

   [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks

   Jupyter Notebook 12

6. ThinkEdit ThinkEdit Public

   An effective weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study uncovering how reasoning length is encoded in the model’s representation space.

   Python 12 2