MilaNLProc / honestLinks
A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.
☆20Updated 10 months ago
Alternatives and similar repositories for honest
Users that are interested in honest are comparing it to the libraries listed below
Sorting:
- Repository for research in the field of Responsible NLP at Meta.☆205Updated last week
- StereoSet: Measuring stereotypical bias in pretrained language models☆198Updated 3 years ago
- This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".☆89Updated 4 years ago
- A repository with several curated datasets of counter-narratives to fight online hate speech.☆94Updated 6 months ago
- Code for the paper "Measuring Bias in Contextualized Word Representations"☆35Updated 6 years ago
- ☆43Updated 2 years ago
- Find informative examples to efficiently (human)-evaluate NLG models.☆18Updated last week
- To analyze and remove gender bias in coreference resolution systems☆78Updated 9 months ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 3 years ago
- Data for evaluating gender bias in coreference resolution systems.☆80Updated 6 years ago
- Code for our WOAH@ACL 2021 Paper on Data Integration for Toxic Comment Classification: Making More Than 40 Datasets Easily Accessible in …☆30Updated 4 years ago
- Code and Data for Evaluation WG☆42Updated 3 years ago
- A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.☆106Updated 2 years ago
- Repo for Aspire - A scientific document similarity model based on matching fine-grained aspects of scientific papers.☆54Updated 2 years ago
- A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, …☆98Updated last year
- Collection of NLP model explanations and accompanying analysis tools☆144Updated 2 years ago
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆50Updated 3 years ago
- A reading list of up-to-date papers on NLP for Social Good.☆305Updated 2 years ago
- A Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation, Levy et al., Findings of EMNLP 2021☆14Updated 3 years ago
- Code to reproduce data for Bias in Bios☆48Updated 2 years ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆154Updated 5 months ago
- Röttger et al. (ACL 2021): "HateCheck: Functional Tests for Hate Speech Detection Models" - Data☆59Updated 3 months ago
- Dataset + classifier tools to study social perception biases in natural language generation☆71Updated 2 years ago
- Learning Gender-Neutral Word Embeddings☆47Updated 6 years ago
- This repository contains a dataset for hate speech detection on social media platforms.☆74Updated 3 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆56Updated 4 years ago
- Attribute statements generated by LLMs to preceding tokens using attention weights.☆21Updated 9 months ago
- Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages (ACL 2022)☆19Updated 3 years ago
- ☆53Updated last year
- A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.☆28Updated last year