IINemo / lm-polygraph
☆116Updated this week
Related projects: ⓘ
- ☆87Updated 2 years ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆36Updated 5 months ago
- ☆23Updated 2 years ago
- Code repository for the paper "Mission: Impossible Language Models".☆27Updated 8 months ago
- ☆27Updated 3 years ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆55Updated 8 months ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆94Updated 10 months ago
- Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.☆45Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆80Updated 3 years ago
- ☆35Updated 2 years ago
- ☆95Updated 2 years ago
- ☆42Updated 7 months ago
- ☆56Updated last year
- ☆92Updated 4 months ago
- ☆26Updated last year
- Distributional Generalization in NLP. A roadmap.☆86Updated last year
- ☆35Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆93Updated last month
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆45Updated 2 years ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆114Updated 11 months ago
- ☆70Updated 10 months ago
- Sparse probing paper full code.☆47Updated 9 months ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆83Updated 2 years ago
- ☆101Updated last year
- Repository for the Bias Benchmark for QA dataset.☆83Updated 8 months ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆39Updated last year
- ☆64Updated last month
- AI Logging for Interpretability and Explainability🔬☆74Updated 3 months ago
- The official code of EMNLP 2022, "SCROLLS: Standardized CompaRison Over Long Language Sequences".☆67Updated 8 months ago
- Measuring the Mixing of Contextual Information in the Transformer☆24Updated last year