{"url":"/task/bias-detection","name":"Bias Detection","slug":"bias-detection","description_markdown":"Bias detection is the task of detecting and measuring racism, sexism and otherwise discriminatory behavior in a model (Source: https://stereoset.mit.edu/)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":199,"papers_with_code":80,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/bias-detection-on-stereoset-1","slug":"bias-detection-on-stereoset-1","dataset":"StereoSet","dataset_url":"/dataset/stereoset","rows_in_archive":11,"metrics":["ICAT Score","LMS","SS"],"first_row_in_archive_order":{"model":"GPT-2 (small)","paper_title":"StereoSet: Measuring stereotypical bias in pretrained language models","paper_url":"/paper/stereoset-measuring-stereotypical-bias-in","paper_date":"2020-04-20","arxiv_id":"2004.09456","code_links":[{"title":"moinnadeem/StereoSet","url":"https://github.com/moinnadeem/StereoSet"},{"title":"kanekomasahiro/evaluate_bias_in_mlm","url":"https://github.com/kanekomasahiro/evaluate_bias_in_mlm"},{"title":"zalkikar/mlm-bias","url":"https://github.com/zalkikar/mlm-bias"}],"syntology":null}},{"leaderboard":"/sota/bias-detection-on-rt-inod-bias","slug":"bias-detection-on-rt-inod-bias","dataset":"rt-inod-bias","dataset_url":"/dataset/rt-inod-bias","rows_in_archive":5,"metrics":["Best-of"],"first_row_in_archive_order":{"model":"GPT-4","paper_title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","paper_url":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","paper_date":"2024-04-15","arxiv_id":"2404.09785","code_links":[{"title":"innodatalabs/innodata-llm-safety","url":"https://github.com/innodatalabs/innodata-llm-safety"}],"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/bias-detection-on-icat-llm-bias","slug":"bias-detection-on-icat-llm-bias","dataset":"ICAT LLM bias","dataset_url":null,"rows_in_archive":1,"metrics":["ICAT Score"],"first_row_in_archive_order":{"model":"BAD","paper_title":"BAD: BiAs Detection for Large Language Models in the context of candidate screening","paper_url":"/paper/bad-bias-detection-for-large-language-models","paper_date":"2023-05-17","arxiv_id":"2305.10407","code_links":[{"title":"namhkoh/bad-bias-detection-in-llms","url":"https://github.com/namhkoh/bad-bias-detection-in-llms"}],"syntology":null}},{"leaderboard":"/sota/bias-detection-on-plantvillage-8px","slug":"bias-detection-on-plantvillage-8px","dataset":"PlantVillage_8px","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"RandomForest_default_hyperparameters","paper_title":"Uncovering bias in the PlantVillage dataset","paper_url":"/paper/uncovering-bias-in-the-plantvillage-dataset","paper_date":"2022-06-09","arxiv_id":"2206.04374","code_links":[{"title":"Ipsumio/plantvillage_bias","url":"https://github.com/Ipsumio/plantvillage_bias"}],"syntology":null}},{"leaderboard":"/sota/bias-detection-on-wiki-neutrality-corpus","slug":"bias-detection-on-wiki-neutrality-corpus","dataset":"Wiki Neutrality Corpus","dataset_url":null,"rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"RoBERTa+ALBERT","paper_title":"Towards Detection of Subjective Bias using Contextualized Word Embeddings","paper_url":"/paper/towards-detection-of-subjective-bias-using","paper_date":"2020-02-16","arxiv_id":"2002.06644","code_links":[{"title":"tanvidadu/Subjective-Bias-Detection","url":"https://github.com/tanvidadu/Subjective-Bias-Detection"}],"syntology":null}}],"datasets":[{"url":"/dataset/stereoset","name":"StereoSet","full_name":"","num_papers_in_archive":156},{"url":"/dataset/basil","name":"BASIL","full_name":"","num_papers_in_archive":27},{"url":"/dataset/grep-biasir","name":"Grep-BiasIR","full_name":"Gender Representation-Bias for Information Retrieval","num_papers_in_archive":5},{"url":"/dataset/ci-mnist","name":"CI-MNIST","full_name":"Correlated and Imbalanced MNIST","num_papers_in_archive":4},{"url":"/dataset/clear-bias","name":"CLEAR-Bias","full_name":"Corpus for Linguistic Evaluation of Adversarial Robustness against Bias","num_papers_in_archive":2},{"url":"/dataset/newb","name":"NewB","full_name":"","num_papers_in_archive":2},{"url":"/dataset/twinviews-13k","name":"TwinViews-13k","full_name":"","num_papers_in_archive":2},{"url":"/dataset/filipino-crows-pairs-and-filipino-winoqueer","name":"Filipino CrowS-Pairs and Filipino WinoQueer","full_name":"","num_papers_in_archive":1},{"url":"/dataset/chicago-face-database-cfd","name":"international faces","full_name":"","num_papers_in_archive":1},{"url":"/dataset/rt-inod-bias","name":"rt-inod-bias","full_name":"Red Teaming Innodata Bias","num_papers_in_archive":1},{"url":"/dataset/weathub","name":"WEATHub","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/selection-bias","name":"Selection bias"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":80,"tagged_in_all":199,"items":[{"url":"/paper/stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","date":"2020-04-20","arxiv_id":"2004.09456","repositories_listed":3,"syntology":null},{"url":"/paper/investigating-subtler-biases-in-llms-ageism","title":"Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models","date":"2023-09-16","arxiv_id":"2309.08902","repositories_listed":2,"syntology":null},{"url":"/paper/bipol-multi-axes-evaluation-of-bias-with","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","date":"2023-01-28","arxiv_id":"2301.12139","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-emergent-intersectional-biases","title":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases","date":"2020-06-06","arxiv_id":"2006.03955","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/diagnostic-curves-for-black-box-models","title":"Automated Dependence Plots","date":"2019-12-02","arxiv_id":"1912.01108","repositories_listed":2,"syntology":null},{"url":"/paper/how-neural-networks-organize-concepts","title":"How Neural Networks Organize Concepts: Introducing Concept Trajectory Analysis for Deep Learning Interpretability","date":"2025-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/to-bias-or-not-to-bias-detecting-bias-in-news","title":"To Bias or Not to Bias: Detecting bias in News with bias-detector","date":"2025-05-19","arxiv_id":"2505.13010","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11189","title":"Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP","date":"2025-05-16","arxiv_id":"2505.11189","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-ai-in-spatial-analysis","title":"Explainable AI in Spatial Analysis","date":"2025-05-01","arxiv_id":"2505.00591","repositories_listed":1,"syntology":null},{"url":"/paper/robust-bias-detection-in-mlms-and-its","title":"Robust Bias Detection in MLMs and its Application to Human Trait Ratings","date":"2025-02-21","arxiv_id":"2502.15600","repositories_listed":1,"syntology":null},{"url":"/paper/vilbias-a-framework-for-bias-detection-using","title":"ViLBias: A Comprehensive Framework for Bias Detection through Linguistic and Visual Cues , presenting Annotation Strategies, Evaluation, and Key Challenges","date":"2024-12-22","arxiv_id":"2412.17052","repositories_listed":1,"syntology":null},{"url":"/paper/mt-lens-an-all-in-one-toolkit-for-better","title":"MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation","date":"2024-12-16","arxiv_id":"2412.11615","repositories_listed":1,"syntology":null},{"url":"/paper/the-promises-and-pitfalls-of-llm-annotations","title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","date":"2024-11-17","arxiv_id":"2411.11081","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-bias-in-queer-representation","title":"Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach","date":"2024-11-12","arxiv_id":"2411.07656","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mapping-bias-in-vision-language-models","title":"debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias","date":"2024-10-17","arxiv_id":"2410.13146","repositories_listed":1,"syntology":null},{"url":"/paper/gus-net-social-bias-classification-in-text","title":"GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes","date":"2024-10-10","arxiv_id":"2410.08388","repositories_listed":1,"syntology":null},{"url":"/paper/tinyemo-scaling-down-emotional-reasoning-via","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","date":"2024-10-09","arxiv_id":"2410.07062","repositories_listed":1,"syntology":null},{"url":"/paper/towards-implicit-bias-detection-and","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","date":"2024-10-03","arxiv_id":"2410.02584","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/counterfactual-token-generation-in-large","title":"Counterfactual Token Generation in Large Language Models","date":"2024-09-25","arxiv_id":"2409.17027","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":10}},{"url":"/paper/explainable-ai-for-computational-pathology","title":"Explainable AI for computational pathology identifies model limitations and tissue biomarkers","date":"2024-09-04","arxiv_id":"2409.03080","repositories_listed":1,"syntology":null},{"url":"/paper/gradbias-unveiling-word-influence-on-bias-in","title":"GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models","date":"2024-08-29","arxiv_id":"2408.16700","repositories_listed":1,"syntology":null},{"url":"/paper/the-bias-detection-framework-bias-detection","title":"The BIAS Detection Framework: Bias Detection in Word Embeddings and Language Models for European Languages","date":"2024-07-26","arxiv_id":"2407.18689","repositories_listed":1,"syntology":null},{"url":"/paper/social-bias-in-large-language-models-for","title":"Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias","date":"2024-07-03","arxiv_id":"2407.03536","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-nationality-bias-in-names-and","title":"A Study of Nationality Bias in Names and Perplexity using Off-the-Shelf Affect-related Tweet Classifiers","date":"2024-07-01","arxiv_id":"2407.01834","repositories_listed":1,"syntology":null},{"url":"/paper/gender-bias-detection-in-court-decisions-a","title":"Gender Bias Detection in Court Decisions: A Brazilian Case Study","date":"2024-06-01","arxiv_id":"2406.00393","repositories_listed":1,"syntology":null},{"url":"/paper/disparisk-assessing-and-interpreting","title":"DispaRisk: Auditing Fairness Through Usable Information","date":"2024-05-20","arxiv_id":"2405.12372","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizrr-generating-diverse-datasets-with","title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation","date":"2024-05-16","arxiv_id":"2405.10040","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","date":"2024-04-15","arxiv_id":"2404.09785","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/openbias-open-set-bias-detection-in-text-to","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","date":"2024-04-11","arxiv_id":"2404.07990","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":10}},{"url":"/paper/denetdm-debiasing-by-network-depth-modulation","title":"DeNetDM: Debiasing by Network Depth Modulation","date":"2024-03-28","arxiv_id":"2403.19863","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}