Jared Fernandez, Clara Na, Vashisth Tiwari, Yonatan Bisk, Sasha Luccioni, Emma Strubell. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This paper introduces the "CIVICS: Culturally-Informed \& Values-Inclusive Corpus for Societal impacts" dataset, designed to evaluate the social and cultural variation of Large Language Models (LLMs) towards socially sensitive topics across multiple languages and cultures. The hand-crafted, multilingual dataset of statements addresses value-laden topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy. CIVICS is designed to elicit responses from LLMs to shed light on how values encoded in their parameters shape their behaviors. Through our dynamic annotation processes, tailored prompt design, and experiments, we investigate how open-weight LLMs respond to these issues, exploring their behavior across diverse linguistic and cultural contexts. Using two experimental set-ups based on log-probabilities and long-form responses, we show social and cultural variability across different LLMs. Specifically, different topics and sources lead to more pronounced differences across model answers, particularly on immigration, LGBTQI rights, and social welfare. Experiments on generating long-form responses from models tuned for user chat demonstrate that refusals are triggered disparately across different models, but consistently and more frequently in English or translated statements. As shown by our initial experimentation, the CIVICS dataset can serve as a tool for future research, promoting reproducibility and transparency across broader linguistic settings, and furthering the development of AI technologies that respect and reflect global cultural diversities and value pluralism. The CIVICS dataset and tools are made available under open licenses at hf.co/CIVICS-dataset.

Much of the recent discourse within the ML community has been centered around Large Language Models (LLMs), their functionality and potential – yet not only do we not have a working definition of LLMs, but much of this discourse relies on claims and assumptions that are worth re-examining. We contribute a definition of LLMs, critically examine five common claims regarding their properties (including ’emergent properties’), and conclude with suggestions for future research directions and their framing.

ImageNet-1k is a dataset often used for benchmarking machine learning (ML) models and evaluating tasks such as image recognition and object detection. Wild animals make up 27% of ImageNet-1k but, unlike classes representing people and objects, these data have not been closely scrutinized. In the current paper, we analyze the 13,450 images from 269 classes that represent wild animals in the ImageNet-1k validation set, with the participation of expert ecologists. We find that many of the classes are ill-defined or overlapping, and that 12% of the images are incorrectly labeled, with some classes having >90% of images incorrect. We also find that both the wildlife-related labels and images included in ImageNet-1k present significant geographical and cultural biases, as well as ambiguities such as artificial animals, multiple species in the same image, or the presence of humans. Our findings highlight serious issues with the extensive use of this dataset for evaluating ML systems, the use of such algorithms in wildlife-related tasks, and more broadly the ways in which ML datasets are commonly created and curated.

`Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied, we are only beginning to scratch the surface of data scaling and its consequences. This is especially of critical importance in the context of vision-language datasets such as LAION. These datasets are continually growing in size and are built based on large-scale internet dumps such as the Common Crawl, which is known to have numerous drawbacks ranging from quality, legality, and content. The datasets then serve as the backbone for large generative models, contributing to the operationalization and perpetuation of harmful societal and historical biases and stereotypes. In this paper, we investigate the effect of scaling datasets on hateful content through a comparative audit of two datasets: LAION-400M and LAION-2B. Our results show that hate content increased by nearly 12% with dataset scale, measured both qualitatively and quantitatively using a metric that we term as Hate Content Rate (HCR). We also found that filtering dataset contents based on Not Safe For Work (NSFW) values calculated based on images alone does not exclude all the harmful content in alt-text. Instead, we found that trace amounts of hateful, targeted, and aggressive text remain even when carrying out conservative filtering. We end with a reflection and a discussion of the significance of our results for dataset curation and usage in the AI community.Code and the meta-data assets curated in this paper are publicly available at https://github.com/vinayprabhu/hate_scaling. Content warning: This paper contains examples of hateful text that might be disturbing, distressing, and/or offensive.

As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly prevalent and seeing growing adoption as commercial services, characterizing the social biases they exhibit is a necessary first step to lowering their risk of discriminatory outcomes. This evaluation, however, is made more difficult by the synthetic nature of these systems’ outputs: common definitions of diversity are grounded in social categories of people living in the world, whereas the artificial depictions of fictive humans created by these systems have no inherent gender or ethnicity. To address this need, we propose a new method for exploring the social biases in TTI systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts, and comparing it to the variation engendered by spanning different professions. This allows us to (1) identify specific bias trends, (2) provide targeted scores to directly compare models in terms of diversity and representation, and (3) jointly model interdependent social variables to support a multidimensional analysis. We leverage this method to analyze images generated by 3 popular TTI systems (Dall·E 2 , Stable Diffusion v 1.4 and 2) and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents. We also release the datasets and low-code interactive bias exploration platforms developed forthis work, as well as the necessary tools to similarly evaluate additional TTI systems.

Progress in machine learning (ML) comes with a cost to the environment, given that training ML models requires computational resources, energy and materials. In the present article, we aim to quantify the carbon footprint of BLOOM, a 176-billion parameter language model, across its life cycle. We estimate that BLOOM’s final training emitted approximately 24.7 tonnes of CO2eq if we consider only the dynamic power consumption, and 50.5 tonnes if we account for all processes ranging from equipment manufacturing to energy-based operational consumption. We also carry out an empirical study to measure the energy requirements and carbon emissions of its deployment for inference via an API endpoint receiving user queries in real-time. We conclude with a discussion regarding the difficulty of precisely estimating the carbon footprint of ML models and future research directions that can contribute towards improving carbon emissions reporting.

As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings. The BigScience workshop, a 1-year international and multidisciplinary initiative, was formed with the goal of researching and training large language models as a values-driven undertaking, putting issues of ethics, harm, and governance in the foreground. This paper documents the data creation and curation efforts undertaken by BigScience to assemble the Responsible Open-science Open-collaboration Text Sources (ROOTS) corpus, a 1.6TB dataset spanning 59 languages that was used to train the 176-billion-parameter BigScience Large Open-science Open-access Multilingual (BLOOM) language model. We further release a large initial subset of the corpus and analyses thereof, and hope to empower large-scale monolingual and multilingual modeling projects with both the data and the processing tools, as well as stimulate research around this large multilingual corpus.

COVID-19, the disease caused by the SARS-CoV-2 virus, has been declared a pandemic by the World Health Organization, which has reported over 18 million confirmed cases as of August 5, 2020. In this review, we present an overview of recent studies using Machine Learning and, more broadly, Artificial Intelligence, to tackle many aspects of the COVID19 crisis. We have identified applications that address challenges posed by COVID-19 at different scales, including: molecular, by identifying new or existing drugs for treatment; clinical, by supporting diagnosis and evaluating prognosis based on medical imaging and non-invasive measures; and societal, by tracking both the epidemic and the accompanying infodemic using multiple data sources. We also review datasets, tools, and resources needed to facilitate Artificial Intelligence research, and discuss strategic considerations related to the operational implementation of multidisciplinary partnerships and open science. We highlight the need for international cooperation to maximize the potential of AI in this and future pandemics.