k-hanawa / criteria_for_instance_based_explanation
☆9Updated last year
Related projects: ⓘ
- ☆22Updated 2 months ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆48Updated 3 years ago
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence…☆16Updated 4 years ago
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆58Updated 6 months ago
- Implementation for Variational Information Bottleneck for Effective Low-resource Fine-tuning, ICLR 2021☆36Updated 3 years ago
- ☆21Updated 7 months ago
- ☆12Updated 3 months ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆12Updated 4 months ago
- ☆38Updated 8 months ago
- https://arxiv.org/abs/2102.12594☆14Updated 11 months ago
- ☆25Updated 3 years ago
- Uncertainty Quantification with Pre-trained Language Models: An Empirical Analysis☆13Updated last year
- ☆15Updated 4 years ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆48Updated 5 months ago
- ☆11Updated 2 years ago
- ☆13Updated 4 months ago
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Updated 11 months ago
- ☆16Updated 8 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆22Updated 2 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆21Updated 9 months ago
- Code for NeurIPS'23 paper "A Bayesian Approach To Analysing Training Data Attribution In Deep Learning"☆14Updated 8 months ago
- Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.☆45Updated last year
- Bayesian low-rank adaptation for large language models☆22Updated 4 months ago
- ☆47Updated last year
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆16Updated 10 months ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 4 months ago
- Code to reproduce the experiments in the paper: Does CLIP Bind Concepts? Probing Compositionality in Large Image Models.☆12Updated 11 months ago
- Source code for paper "Contrastive Out-of-Distribution Detection for Pretrained Transformers", EMNLP 2021☆40Updated 2 years ago
- N/A☆18Updated 2 years ago