{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","arxiv_id":null,"date":"2021-06-01","proceeding":"NAACL 2021 4","authors":["Debora Nozza","Federico Bianchi","Dirk Hovy"],"abstract":"Language models have revolutionized the field of NLP. However, language models capture and proliferate hurtful stereotypes, especially in text generation. Our results show that 4.3{\\%} of the time, language models complete a sentence with a hurtful word. These cases are not random, but follow language and gender-specific patterns. We propose a score to measure hurtful sentence completions in language models (HONEST). It uses a systematic template- and lexicon-based bias evaluation methodology for six languages. Our findings suggest that these models replicate and amplify deep-seated societal stereotypes about gender roles. Sentence completions refer to sexual promiscuity when the target is female in 9{\\%} of the time, and in 4{\\%} to homosexuality when the target is male. The results raise questions about the use of these models in production settings.","url_abs":"https://aclanthology.org/2021.naacl-main.191","url_pdf":"https://aclanthology.org/2021.naacl-main.191.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"honest-measuring-hurtful-sentence-completion","repo_url":"https://github.com/milanlproc/honest","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"hate-speech-detection","task_name":"Hate Speech Detection"},{"task_slug":"hurtful-sentence-completion","task_name":"Hurtful Sentence Completion"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-completion","task_name":"Sentence Completion"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"distilbert","method_name":"DistilBERT"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"honest-en","name":"HONEST","full_name":"Hurtful Sentence Completion in English Language Models"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset":"HONEST","model":"BERT-base","rank_in_archive_order":1,"of":5,"metrics":{"HONEST":"1.19"},"uses_additional_data":false},{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset":"HONEST","model":"DistilBERT-base","rank_in_archive_order":2,"of":5,"metrics":{"HONEST":"1.90"},"uses_additional_data":false},{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset":"HONEST","model":"RoBERTa-base","rank_in_archive_order":3,"of":5,"metrics":{"HONEST":"2.38"},"uses_additional_data":false},{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset":"HONEST","model":"RoBERTa-large","rank_in_archive_order":4,"of":5,"metrics":{"HONEST":"2.62"},"uses_additional_data":false},{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset":"HONEST","model":"BERT-large","rank_in_archive_order":5,"of":5,"metrics":{"HONEST":"3.33"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}