--- title: "Bias, fairness & safety — papers, page 2" description: "Bias, fairness & safety: 160 papers of the Elamur Research library · page 2 of 7, the most cited first." canonical: "https://research.elamur.ai/free/en/topics/bias-fairness-safety/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/topics/bias-fairness-safety/page/2/) [home](https://md.research.elamur.ai/free/en/) / [topics](https://md.research.elamur.ai/free/en/topics/) / [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) / page 2 # 🛡️ Bias, fairness & safety 160 papers · page 2 of 7 · the most cited first · [all topics](https://md.research.elamur.ai/free/en/topics/) Harmful outputs, social bias and the alignment of language systems with human values. [← prev](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) [1](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) **2** [3](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/3/) … [7](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/7/) [next →](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/3/) - [Evaluating Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/stanovsky-2019-evaluating-gender-bias-machine-translation/) — Gabriel Stanovsky, Noah A. Smith, Luke Zettlemoyer · 2019 · 588 citations - [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://md.research.elamur.ai/free/en/papers/davidson-2019-racial-bias-hate-speech-abusive/) — Thomas Davidson, Debasmita Bhattacharya, Ingmar Weber · 2019 · 577 citations - [Hate Speech Dataset from a White Supremacy Forum](https://md.research.elamur.ai/free/en/papers/gibert-2018-hate-speech-dataset-white-supremacy/) — Ona de Gibert, Naiara Perez, Aitor García-Pablos, et al. · 2018 · 577 citations - [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/) — Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, et al. · 2022 · 571 citations - [Jailbreaking Black Box Large Language Models in Twenty Queries](https://md.research.elamur.ai/free/en/papers/chao-2023-jailbreaking-black-box-large-language/) — Patrick Chao, Alexander Robey, Edgar Dobriban, et al. · 2023 · 533 citations - [Gender Bias in Contextualized Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/) — Jieyu Zhao, Tianlu Wang, Mark Yatskar, et al. · 2019 · 503 citations - [BBQ: A hand-built bias benchmark for question answering](https://md.research.elamur.ai/free/en/papers/parrish-2022-bbq-hand-built-bias-benchmark/) — Alicia Parrish, Angelica Chen, Nikita Nangia, et al. · 2022 · 487 citations - [Reducing Gender Bias in Abusive Language Detection](https://md.research.elamur.ai/free/en/papers/park-2018-reducing-gender-bias-abusive-language/) — Ji Ho Park, Jamin Shin, Pascale Fung · 2018 · 464 citations - [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://md.research.elamur.ai/free/en/papers/ganguli-2022-red-teaming-language-models-reduce/) — Deep Ganguli, Liane Lovitt, Jackson Kernion, et al. · 2022 · 456 citations - [GeDi: Generative Discriminator Guided Sequence Generation](https://md.research.elamur.ai/free/en/papers/krause-2021-gedi-generative-discriminator-guided-sequence/) — Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, et al. · 2021 · 444 citations - [Ethical and social risks of harm from Language Models](https://md.research.elamur.ai/free/en/papers/weidinger-2021-ethical-social-risks-harm-language/) — Laura Weidinger, John Mellor, Maribeth Rauh, et al. · 2021 · 421 citations - [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://md.research.elamur.ai/free/en/papers/gonen-2019-lipstick-pig-debiasing-methods-cover/) — Hila Gonen, Yoav Goldberg · 2019 · 412 citations - [Multilingual and Multi-Aspect Hate Speech Analysis](https://md.research.elamur.ai/free/en/papers/ousidhoum-2019-multilingual-multi-aspect-hate-speech/) — Nedjma Ousidhoum, Zizheng Lin, Hongming Zhang, et al. · 2019 · 408 citations - [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://md.research.elamur.ai/free/en/papers/kiela-2020-hateful-memes-challenge-detecting-hate/) — Douwe Kiela, Hamed Firooz, Aravind Mohan, et al. · 2020 · 403 citations - [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://md.research.elamur.ai/free/en/papers/hutchinson-2020-social-biases-nlp-models-as/) — Ben Hutchinson, Vinodkumar Prabhakaran, Emily Denton, et al. · 2020 · 402 citations - [Gender Bias in Neural Natural Language Processing](https://md.research.elamur.ai/free/en/papers/lu-2018-gender-bias-neural-natural-language/) — Kaiji Lu, Piotr Mardziel, Fangjing Wu, et al. · 2018 · 394 citations - [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://md.research.elamur.ai/free/en/papers/zmigrod-2019-counterfactual-data-augmentation-mitigating-gender/) — Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, et al. · 2019 · 371 citations - [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://md.research.elamur.ai/free/en/papers/sap-2022-annotators-attitudes-how-annotator-beliefs/) — Maarten Sap, Swabha Swayamdipta, Laura Vianna, et al. · 2022 · 364 citations - [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://md.research.elamur.ai/free/en/papers/elsherief-2021-latent-hatred-benchmark-understanding-implicit/) — Mai ElSherief, Caleb Ziems, David Muchlinski, et al. · 2021 · 364 citations - [Identifying and Reducing Gender Bias in Word-Level Language Models](https://md.research.elamur.ai/free/en/papers/bordia-2019-identifying-reducing-gender-bias-word/) — Shikha Bordia, Samuel R. Bowman · 2019 · 363 citations - [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://md.research.elamur.ai/free/en/papers/ji-2023-beavertails-towards-improved-safety-alignment/) — Jiaming Ji, Mickel Liu, Juntao Dai, et al. · 2023 · 351 citations - [Toxicity in chatgpt: Analyzing persona-assigned language models](https://md.research.elamur.ai/free/en/papers/deshpande-2023-toxicity-chatgpt-analyzing-persona-assigned/) — Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, et al. · 2023 · 344 citations - [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://md.research.elamur.ai/free/en/papers/liu-2023-autodan-generating-stealthy-jailbreak-prompts/) — Xiaogeng Liu, Nan Xu, Muhao Chen, et al. · 2023 · 333 citations - [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://md.research.elamur.ai/free/en/papers/qi-2023-fine-tuning-aligned-language-models/) — Xiangyu Qi, Yi Zeng, Tinghao Xie, et al. · 2023 · 331 citations - ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://md.research.elamur.ai/free/en/papers/shen-2023-anything-now-characterizing-evaluating-wild/) — Xinyue Shen, Zeyuan Chen, Michael Backes, et al. · 2023 · 320 citations [← prev](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) [1](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) **2** [3](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/3/) … [7](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/7/) [next →](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/page/3/)