This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".
☆89Aug 20, 2021Updated 4 years ago
Alternatives and similar repositories for self-debiasing
Users that are interested in self-debiasing are comparing it to the libraries listed below
Sorting:
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆154Aug 18, 2025Updated 6 months ago
- Data and code for the paper "The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems"☆21Jul 18, 2023Updated 2 years ago
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆38Dec 14, 2023Updated 2 years ago
- [ACL 2020] Towards Debiasing Sentence Representations☆64Nov 21, 2022Updated 3 years ago
- Dataset + classifier tools to study social perception biases in natural language generation☆71Jun 12, 2023Updated 2 years ago
- PyTorch implementation of NAACL 2021 paper "Multi-view Subword Regularization"☆26Jun 2, 2021Updated 4 years ago
- Scripts to evaluate various bias metrics for different NLG models + decoding algorithms☆16Dec 6, 2023Updated 2 years ago
- code associated with ACL 2021 DExperts paper☆118May 24, 2023Updated 2 years ago
- This repository contains the code for "Generating Datasets with Pretrained Language Models".☆189Aug 17, 2021Updated 4 years ago
- Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper☆86Mar 2, 2021Updated 4 years ago
- ☆14Sep 17, 2020Updated 5 years ago
- ☆13Apr 16, 2021Updated 4 years ago
- Papers on fairness in NLP☆452May 2, 2024Updated last year
- ☆23Jun 30, 2025Updated 8 months ago
- Narrative Understanding Workshop paper (2021) on gender in GPT-3 generated stories☆14May 28, 2021Updated 4 years ago
- Highly specialized crate to parse and use `google/sentencepiece` 's precompiled_charsmap in `tokenizers`☆20Jan 8, 2026Updated last month
- ☆229Feb 23, 2021Updated 5 years ago
- Code for our WOAH@ACL 2021 Paper on Data Integration for Toxic Comment Classification: Making More Than 40 Datasets Easily Accessible in …☆30Nov 25, 2021Updated 4 years ago
- A Framework aims to wisely initialize unseen subword embeddings in PLMs for efficient large-scale continued pretraining☆18Nov 26, 2023Updated 2 years ago
- ☆71Oct 29, 2021Updated 4 years ago
- ☆46Jan 26, 2020Updated 6 years ago
- Course for Interpreting ML Models☆52Feb 16, 2023Updated 3 years ago
- 🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models☆12May 30, 2025Updated 9 months ago
- GeDi: Generative Discriminator Guided Sequence Generation☆211Jun 16, 2025Updated 8 months ago
- code for modular summarization work published in ACL2021 by Krishna et al☆30Nov 4, 2021Updated 4 years ago
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆20Jun 12, 2023Updated 2 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆56May 23, 2021Updated 4 years ago
- ☆25Feb 6, 2022Updated 4 years ago
- Concealed Data Poisoning Attacks on NLP Models☆21Sep 4, 2023Updated 2 years ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Nov 2, 2022Updated 3 years ago
- ☆68May 18, 2023Updated 2 years ago
- ☆21Sep 21, 2021Updated 4 years ago
- A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.☆21Apr 8, 2025Updated 10 months ago
- ☆90Jun 6, 2022Updated 3 years ago
- Long-context pretrained encoder-decoder models☆96Oct 28, 2022Updated 3 years ago
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https…☆44Aug 10, 2024Updated last year
- Server and dashboard components☆12Jun 24, 2024Updated last year
- stateless model checking for thread libraries, kernels, and transactional memory☆10Dec 26, 2018Updated 7 years ago
- Dynamic analysis of multithreaded C programs☆13Feb 7, 2020Updated 6 years ago