Kaleidophon / nlp-uncertainty-zoo
Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.
☆47Updated last year
Related projects ⓘ
Alternatives and complementary repositories for nlp-uncertainty-zoo
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆95Updated last year
- How certain is your transformer?☆25Updated 3 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆69Updated last year
- "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)☆82Updated last year
- ☆25Updated 4 months ago
- ☆29Updated 3 years ago
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 3 years ago
- This is reimplementation of "Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness" in Pyt…☆47Updated 3 years ago
- ☆17Updated 10 months ago
- ☆24Updated 3 years ago
- Implementation for Variational Information Bottleneck for Effective Low-resource Fine-tuning, ICLR 2021☆38Updated 3 years ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆35Updated last year
- Code for Residual Energy-Based Models for Text Generation in PyTorch.☆23Updated 3 years ago
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆14Updated last month
- ☆17Updated 9 months ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆42Updated last year
- ☆23Updated 2 years ago
- ☆51Updated last year
- ☆77Updated 4 months ago
- Distributional Generalization in NLP. A roadmap.☆87Updated last year
- The Codebase for Causal Distillation for Language Models (NAACL '22)☆25Updated 2 years ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆42Updated 7 months ago
- Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"☆16Updated 2 years ago
- ☆58Updated 2 years ago
- ☆103Updated 2 years ago
- ☆33Updated 3 years ago
- [EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.☆24Updated last year
- Teaching Models to Express Their Uncertainty in Words☆36Updated 2 years ago
- ☆26Updated 9 months ago
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago