INK-USC / DIGLinks
Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)
☆28Updated 3 years ago
Alternatives and similar repositories for DIG
Users that are interested in DIG are comparing it to the libraries listed below
Sorting:
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆34Updated 4 years ago
- ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation☆24Updated 3 years ago
- Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"☆13Updated 3 years ago
- ☆24Updated 2 years ago
- ☆24Updated 4 years ago
- Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"☆23Updated 4 years ago
- ☆24Updated 2 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Updated 4 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆22Updated 5 years ago
- ☆35Updated 4 years ago
- IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization☆12Updated 4 years ago
- This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"☆19Updated 3 years ago
- ☆47Updated last year
- NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790☆27Updated 3 years ago
- Source code for ICLR 2021 paper : Pre-training Text-to-Text Transformers for Concept-Centric Common Sense☆27Updated 4 years ago
- The data and code for NumerSense (EMNLP2020)☆19Updated 2 years ago
- [EMNLP 2020] Collective HumAn OpinionS on Natural Language Inference Data☆40Updated 3 years ago
- Code for the paper "Refining Language Model with Compositional Explanation" (NeurIPS 2021)☆12Updated 4 years ago
- ☆58Updated 3 years ago
- ☆54Updated 2 years ago
- Code for the paper "REV: Information-Theoretic Evaluation of Free-Text Rationales"☆16Updated 2 years ago
- Explaining neural decisions contrastively to alternative decisions.☆25Updated 4 years ago
- The code for lifelong few-shot language learning☆55Updated 3 years ago
- NILE : Natural Language Inference with Faithful Natural Language Explanations☆30Updated 2 years ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆85Updated 3 years ago
- DEMix Layers for Modular Language Modeling☆54Updated 4 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆32Updated 2 years ago
- ☆45Updated 4 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Updated 2 years ago
- ☆39Updated 4 years ago