NLP models trained on text have been shown to reproduce human stereotypes, which can magnify harms to marginalized groups when systems are deployed at scale. We adapt the Agency-Belief-Communion (ABC) stereotype model of Koch et al. (2016) from social psychology as a framework for the systematic study and discovery of stereotypic group-trait associations in language models (LMs). We introduce the sensitivity test (SeT) for measuring stereotypical associations from language models. To evaluate SeT and other measures using the ABC model, we collect group-trait judgments from U.S.-based subjects to compare with English LM stereotypes. Finally, we extend this framework to measure LM stereotyping of intersectional identities.
MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs
Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）；Center for Language and Cognition, University of Groningen（格罗宁根大学语言与认知中心）
Manipal Institute of Technology（马尼帕尔理工学院）；MAHE（马尼帕尔高等教育学院）；University of Texas, Austin（德克萨斯大学奥斯汀分校）
As the use of natural language processing increases in our day-to-day life, the need to address gender bias inherent in these systems also amplifies. This is because the inherent bias interferes with the semantic structure of the output of these systems while performing tasks like machine translation. While research is being done in English to quantify and mitigate bias, debiasing methods in Indic Languages are either relatively nascent or absent for some Indic languages altogether. Most Indic languages are gendered, i.e., each noun is assigned a gender according to each language's grammar rul…
University of Cambridge（剑桥大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Microsoft Research（微软研究院）
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages. We present a novel approach for converting between masculine-inflected and feminine-inflected sentences in such languages. For Spanish and Hebrew, our approach achieves F1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms. By evaluating our appr…
University of Groningen（格罗宁根大学）；University of Malta（马耳他大学）
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018…
Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech
Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）；I3S（I3S实验室）；PRHLT Research Center, Universitat Politècnica de València（瓦伦西亚理工大学PRHLT研究中心）；ValgrAI Valencian Graduate School and Research Network of Artificial Intelligence（ValgrAI瓦伦西亚人工智能研究生院与研究网络）
Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts
Graduate School of Science and Technology, University of Tsukuba（筑波大学科学技术研究科）；Institute of Systems and Information Engineering, University of Tsukuba（筑波大学系统与信息工程学院）；Department of Electronics, Information and Bioengineering, Politecnico di Milano（米兰理工大学电子、信息与生物工程系）
Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded Audit
Northeastern University（东北大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Southern Methodist University（南卫理公会大学）
We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically different languages. We also draw parallels between artificial neural attention and human attention and show that neural attention focuses on word endings as it has been theorised for human attention. Finally, we investigate how two visually grounded monolingual models can be used to perform cross-lingual speech-to-speech retrieval. For both langua…
Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translation
iApp Technology（iApp科技公司）；Intelligent Informatics and Service Innovation Research Center（智能信息学与服务创新研究中心）；Artificial Intelligence Entrepreneur Association of Thailand (AIEAT)（泰国人工智能企业家协会）；Sirindhorn International Institute of Technology, Thammasat University（诗琳通国际理工学院，法政大学）
As Machine Translation (MT) has become increasingly more powerful, accessible, and widespread, the potential for the perpetuation of bias has grown alongside its advances. While overt indicators of bias have been studied in machine translation, we argue that covert biases expose a problem that is further entrenched. Through the use of the gender-neutral language Turkish and the gendered language English, we examine cases of both overt and covert gender bias in MT models. Specifically, we introduce a method to investigate asymmetrical gender markings. We also assess bias in the attribution of p…
Limited Stereotype Control Through Routing Reweighting in MoE Language Models
Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine（首尔大学医学院癌症生物学跨学科项目）；Department of Radiology, Seoul National University Hospital（首尔大学医院放射科）；Department of Radiology, Seoul National University College of Medicine（首尔大学医学院放射科）；Healthcare AI Research Institute, Seoul National University Hospital（首尔大学医院医疗AI研究所）
Do Multilingual Large Language Models Mitigate Stereotype Bias?
Conversational AI and Social Analytics (CAISA) Lab, University of Bonn（波恩大学）；Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS)（弗劳恩霍夫智能分析与信息系统研究所）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习和人工智能研究所）
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
Department of Electrical and Computer Engineering, Maroun Semaan Faculty of Engineering and Architecture（电气与计算机工程系，马鲁恩·塞马安工程与建筑学院）；American University of Beirut（贝鲁特美国大学）
