amirfeder / CausaLM
CausaLM: Causal Model Explanation Through Counterfactual Language Models
☆55Updated 4 years ago
Alternatives and similar repositories for CausaLM:
Users that are interested in CausaLM are comparing it to the libraries listed below
- Code for paper "When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data"☆14Updated 4 years ago
- Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"☆17Updated 4 years ago
- Official code for the paper "PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains".☆51Updated 3 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆21Updated 4 years ago
- ☆15Updated 3 years ago
- Interpretable Neural Predictions with Differentiable Binary Variables☆84Updated 4 years ago
- ☆49Updated last year
- [ACL 2020] Towards Debiasing Sentence Representations☆65Updated 2 years ago
- code and data for EMNLP-19 paper "Counterfactual Story Reasoning and Generation" https://arxiv.org/abs/1909.04076☆101Updated 5 years ago
- ☆24Updated last year
- Code for Paper: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data☆35Updated 4 years ago
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 3 years ago
- WinoWhy provides human-annotated reasons for answering WSC questions.☆18Updated 4 years ago
- Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)☆27Updated 3 years ago
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆21Updated 2 years ago
- ☆26Updated 2 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆32Updated last year
- Tensorflow implementation of Invariant Rationalization☆49Updated 2 years ago
- NILE : Natural Language Inference with Faithful Natural Language Explanations☆30Updated last year
- ☆17Updated 4 years ago
- ☆17Updated 4 years ago
- Source code for ICLR 2021 paper : Pre-training Text-to-Text Transformers for Concept-Centric Common Sense☆27Updated 3 years ago
- The codes for our ACL'22 paper: PRBOOST: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning.☆35Updated 3 years ago
- ☆26Updated 4 years ago
- Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers☆20Updated 4 years ago
- ☆71Updated last year
- A dataset for realistic evaluation of noisy label methods☆14Updated last year
- code for paper "Improving Sequence-to-Sequence Learning via Optimal Transport"☆67Updated 5 years ago
- A unified approach to explain conditional text generation models. Pytorch. The code of paper "Local Explanation of Dialogue Response Gene…☆17Updated 3 years ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 2 years ago