Algorithmic harms are commonly categorized as either allocative or representational. This study specifically addresses the latter, focusing on an examination of current definitions of representational harms to discern what is included and what is not. This analysis motivates our expansion beyond behavioral definitions to encompass harms to cognitive and affective states. The paper outlines high-level requirements for measurement: identifying the necessary expertise to implement this approach and illustrating it through a case study. Our work highlights the unique vulnerabilities of large language models to perpetrating representational harms, particularly when these harms go unmeasured and unmitigated. The work concludes by presenting proposed mitigations and delineating when to employ them. The overarching aim of this research is to establish a framework for broadening the definition of representational harms and to translate insights from fairness research into practical measurement and mitigation praxis.
Large-scale Pre-Trained Language Models (PTLMs) capture knowledge from massive human-written data which contains latent societal biases and toxic contents. In this paper, we leverage the primary task of PTLMs, i.e., language modeling, and propose a new metric to quantify manifested implicit representational harms in PTLMs towards 13 marginalized demographics. Using this metric, we conducted an empirical analysis of 24 widely used PTLMs. Our analysis provides insights into the correlation between the proposed metric in this work and other related metrics for representational harm. We observe th…
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs…
KU Leuven（鲁汶大学）；Leuven.AI institute（鲁汶人工智能研究所）；TU Berlin（柏林工业大学）；Weizenbaum Institute（魏泽鲍姆研究所）
Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing stereotypes. However, detecting and mitigating these harms is difficult to do in general and becomes computationally expensive when tackling multiple languages or when considering different biases. To address this, we present FairDistillation: a cross-lingual method based on knowledge distillation to construct smaller language models while controlling for specific bias…
Many educational technologies use artificial intelligence (AI) that presents generated or produced language to the learner. We contend that all language, including all AI communication, encodes information about the identity of the human or humans who contributed to crafting the language. With AI communication, however, the user may index identity information that does not match the source. This can lead to representational harms if language associated with one cultural group is presented as "standard" or "neutral", if the language advantages one group over another, or if the language reinforc…
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression
Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）；Google DeepMind（谷歌DeepMind）；Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）
Previous work has largely considered the fairness of image captioning systems through the underspecified lens of "bias." In contrast, we present a set of techniques for measuring five types of representational harms, as well as the resulting measurements obtained for two of the most popular image captioning datasets using a state-of-the-art image captioning system. Our goal was not to audit this image captioning system, but rather to develop normatively grounded measurement techniques, in turn providing an opportunity to reflect on the many challenges involved. We propose multiple measurement …
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Huazhong University of Science and Technology（华中科技大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanyang Technological University（南洋理工大学）
"I don't see myself represented here at all": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities
