k-hanawa / criteria_for_instance_based_explanationLinks
☆9Updated last year
Alternatives and similar repositories for criteria_for_instance_based_explanation
Users that are interested in criteria_for_instance_based_explanation are comparing it to the libraries listed below
Sorting:
- ☆30Updated 11 months ago
- This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence…☆16Updated 5 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 4 years ago
- ☆40Updated 2 years ago
- ☆35Updated 6 months ago
- ☆11Updated 3 years ago
- ☆14Updated 5 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆31Updated 4 years ago
- ☆30Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 5 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆27Updated last year
- ☆17Updated 4 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆54Updated 2 years ago
- Official code repository for Correct-N-Contrast☆22Updated 2 years ago
- ☆25Updated 2 weeks ago
- ☆41Updated 8 months ago
- ☆29Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 9 months ago
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Updated last year
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆18Updated last year
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆38Updated 2 years ago
- ☆26Updated 4 years ago
- ☆11Updated 3 years ago
- ☆40Updated last year
- ☆18Updated last year
- ☆44Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year