MilaNLProc / honestLinks
A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.
☆21Updated 2 months ago
Alternatives and similar repositories for honest
Users that are interested in honest are comparing it to the libraries listed below
Sorting:
- Find informative examples to efficiently (human)-evaluate NLG models.☆11Updated 2 weeks ago
- A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, …☆85Updated last year
- ☆40Updated last year
- Code and Data for Evaluation WG☆41Updated 3 years ago
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆49Updated 3 years ago
- Code for the paper "Measuring Bias in Contextualized Word Representations"☆35Updated 5 years ago
- Dataset + classifier tools to study social perception biases in natural language generation☆69Updated 2 years ago
- Cross-lingual version of WEAT☆9Updated 6 years ago
- This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".☆88Updated 3 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
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆85Updated 3 years ago
- ☆76Updated 3 years ago
- A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.☆27Updated 9 months ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 2 years ago
- StereoSet: Measuring stereotypical bias in pretrained language models☆184Updated 2 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆56Updated 4 years ago
- Repro is a library for easily running code from published papers via Docker.☆40Updated last year
- Data for evaluating gender bias in coreference resolution systems.☆77Updated 6 years ago
- To analyze and remove gender bias in coreference resolution systems☆79Updated last month
- A repository with several curated datasets of counter-narratives to fight online hate speech.☆89Updated 2 years ago
- ☆30Updated 2 years ago
- ☆89Updated 3 years ago
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆138Updated 6 months ago
- Learning Gender-Neutral Word Embeddings☆47Updated 5 years ago
- Official code release for ACL 2020 paper "Contextualizing Hate Speech Classifiers with Post hoc Explanation"☆35Updated 3 years ago
- ☆14Updated last year
- code associated with ACL 2021 DExperts paper☆115Updated 2 years ago
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆20Updated 2 years ago
- Code for our WOAH@ACL 2021 Paper on Data Integration for Toxic Comment Classification: Making More Than 40 Datasets Easily Accessible in …☆29Updated 3 years ago
- ☆39Updated 6 years ago