Networks-Learning / counterfactual-llmsLinks
Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.
☆29Updated 11 months ago
Alternatives and similar repositories for counterfactual-llms
Users that are interested in counterfactual-llms are comparing it to the libraries listed below
Sorting:
- Extending Conformal Prediction to LLMs☆67Updated last year
- Understanding how features learned by neural networks evolve throughout training☆39Updated 11 months ago
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 3 years ago
- Unofficial implementation of Conformal Language Modeling by Quach et al☆29Updated 2 years ago
- Minimum Description Length probing for neural network representations☆20Updated 8 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Implementations of growing and pruning in neural networks☆22Updated 2 years ago
- Quantification of Uncertainty with Adversarial Models☆29Updated 2 years ago
- ☆69Updated last year
- AutoML Two-Sample Test☆19Updated 3 years ago
- ☆32Updated last year
- Ranking of fine-tuned HF models as base models.☆36Updated 2 weeks ago
- Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning☆33Updated 8 months ago
- Google Research☆46Updated 2 years ago
- Code for "Improving Expert Predictions with Conformal Prediction" , ICML 2023☆12Updated last year
- ☆14Updated last year
- This is the repository for the CONFLARE (CONformal LArge language model REtrieval) Python package.☆20Updated last year
- Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.☆44Updated 7 months ago
- Portfolio REgret for Confidence SEquences☆20Updated 9 months ago
- Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding☆23Updated 2 years ago
- Code for minimum-entropy coupling.☆32Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Official implementation of the paper "Interventions, Where and How? Experimental Design for Causal Models at Scale", NeurIPS 2022.☆20Updated 2 years ago
- 📰 Computing the information content of trained neural networks☆22Updated 4 years ago
- Aioli: A unified optimization framework for language model data mixing☆27Updated 8 months ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆16Updated 2 years ago
- Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inf…☆25Updated 11 months ago
- ☆65Updated 10 months ago
- Entailment self-training☆25Updated 2 years ago
- Documentation for dynamic machine learning systems.☆29Updated last year