copenlu / xai-benchmark
A Diagnostic Study of Explainability Techniques for Text Classification
☆67Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for xai-benchmark
- ☆87Updated 2 years ago
- A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/☆97Updated last year
- ☆27Updated last year
- [ACL 2020] Towards Debiasing Sentence Representations☆61Updated last year
- ☆63Updated 4 years ago
- On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification☆30Updated last year
- Source code for "Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models", ICLR 2020.☆30Updated 4 years ago
- Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (h…☆81Updated 3 years ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆60Updated 2 years ago
- ☆38Updated last year
- ☆38Updated last year
- ☆37Updated 3 years ago
- ☆95Updated 2 years ago
- ☆37Updated 5 years ago
- ☆26Updated 2 years ago
- ☆24Updated 3 years ago
- NILE : Natural Language Inference with Faithful Natural Language Explanations☆29Updated last year
- ☆42Updated 9 months ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆54Updated 3 years ago
- This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"☆19Updated 2 years ago
- ☆57Updated last year
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆84Updated 2 years ago
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆19Updated last year
- ☆84Updated last year
- Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.☆48Updated 3 years ago
- ☆19Updated 2 years ago
- Pytorch implementation of DiffMask☆55Updated last year
- Dataset + classifier tools to study social perception biases in natural language generation☆66Updated last year
- Code and datasets for the EMNLP 2020 paper "Calibration of Pre-trained Transformers"☆55Updated last year
- Rationales for Sequential Predictions☆40Updated 2 years ago