copenlu / xai-benchmark
A Diagnostic Study of Explainability Techniques for Text Classification
☆66Updated 4 years ago
Alternatives and similar repositories for xai-benchmark:
Users that are interested in xai-benchmark are comparing it to the libraries listed below
- On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification☆30Updated 2 years ago
- A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/☆96Updated 2 years ago
- ☆64Updated 4 years ago
- ☆27Updated last year
- [ACL 2020] Towards Debiasing Sentence Representations☆64Updated 2 years ago
- ☆97Updated 2 years ago
- ☆89Updated 2 years ago
- Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.☆49Updated 4 years ago
- ☆38Updated last year
- Source code for "Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models", ICLR 2020.☆30Updated 4 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆54Updated 3 years ago
- Official code release for ACL 2020 paper "Contextualizing Hate Speech Classifiers with Post hoc Explanation"☆35Updated 3 years ago
- ☆39Updated 3 years ago
- NILE : Natural Language Inference with Faithful Natural Language Explanations☆30Updated last year
- ☆44Updated last year
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 2 years ago
- Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"☆17Updated 4 years ago
- Implementation for https://arxiv.org/abs/2005.00652☆28Updated 2 years ago
- This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"☆19Updated 2 years ago
- ☆43Updated 5 years ago
- Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"☆59Updated last year
- ☆24Updated 3 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆69Updated 7 months ago
- Perspectrum: a dataset of claims, perspectives and evidence documents☆33Updated 5 years ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆85Updated 2 years ago
- Code for TACL 2020 paper "An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models"☆14Updated 4 years ago
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆20Updated last year
- Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (h…☆81Updated 4 years ago
- Baseline for ERASER benchmark☆17Updated 2 years ago
- Symmetric evaluation set based on the FEVER (fact verification) dataset☆52Updated 3 years ago