Susan Leavy

Susan Leavy, Emilie Pine, Mark T Keane

We present a text mining system to support the exploration of large volumes of text detailing the findings of government inquiries. Despite their historical significance and potential societal impact, key findings of inquiries are often hidden within lengthy documents and remain inaccessible to the general public. We transform the findings of the Irish government's inquiry into industrial schools and through the use of word embedding, text classification and visualisation, present an interactive web-based platform that enables the exploration of the text to uncover new historical insights.

Susan Leavy, Gerardine Meaney, Karen Wade et al.

The increasing availability of digital collections of historical and contemporary literature presents a wealth of possibilities for new research in the humanities. The scale and diversity of such collections however, presents particular challenges in identifying and extracting relevant content. This paper presents Curatr, an online platform for the exploration and curation of literature with machine learning-supported semantic search, designed within the context of digital humanities scholarship. The platform provides a text mining workflow that combines neural word embeddings with expert domain knowledge to enable the generation of thematic lexicons, allowing researches to curate relevant sub-corpora from a large corpus of 18th and 19th century digitised texts.

Abhishek Mandal, Susan Leavy, Suzanne Little

Generative multimodal models based on diffusion models have seen tremendous growth and advances in recent years. Models such as DALL-E and Stable Diffusion have become increasingly popular and successful at creating images from texts, often combining abstract ideas. However, like other deep learning models, they also reflect social biases they inherit from their training data, which is often crawled from the internet. Manually auditing models for biases can be very time and resource consuming and is further complicated by the unbounded and unconstrained nature of inputs these models can take. Research into bias measurement and quantification has generally focused on small single-stage models working on a single modality. Thus the emergence of multistage multimodal models requires a different approach. In this paper, we propose Multimodal Composite Association Score (MCAS) as a new method of measuring gender bias in multimodal generative models. Evaluating both DALL-E 2 and Stable Diffusion using this approach uncovered the presence of gendered associations of concepts embedded within the models. We propose MCAS as an accessible and scalable method of quantifying potential bias for models with different modalities and a range of potential biases.

Marion Bartl, Susan Leavy

Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive. The focus of our work are gender-exclusive affixes in English, such as in 'show-girl' or 'man-cave', which can perpetuate gender stereotypes and binary conceptions of gender. We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the 'Tiny Heap'. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.

Abhishek Mandal, Susan Leavy, Suzanne Little

Deep neural networks used in computer vision have been shown to exhibit many social biases such as gender bias. Vision Transformers (ViTs) have become increasingly popular in computer vision applications, outperforming Convolutional Neural Networks (CNNs) in many tasks such as image classification. However, given that research on mitigating bias in computer vision has primarily focused on CNNs, it is important to evaluate the effect of a different network architecture on the potential for bias amplification. In this paper we therefore introduce a novel metric to measure bias in architectures, Accuracy Difference. We examine bias amplification when models belonging to these two architectures are used as a part of large multimodal models, evaluating the different image encoders of Contrastive Language Image Pretraining which is an important model used in many generative models such as DALL-E and Stable Diffusion. Our experiments demonstrate that architecture can play a role in amplifying social biases due to the different techniques employed by the models for feature extraction and embedding as well as their different learning properties. This research found that ViTs amplified gender bias to a greater extent than CNNs

Marion Bartl, Susan Leavy

This paper presents a new method for automatically detecting words with lexical gender in large-scale language datasets. Currently, the evaluation of gender bias in natural language processing relies on manually compiled lexicons of gendered expressions, such as pronouns ('he', 'she', etc.) and nouns with lexical gender ('mother', 'boyfriend', 'policewoman', etc.). However, manual compilation of such lists can lead to static information if they are not periodically updated and often involve value judgments by individual annotators and researchers. Moreover, terms not included in the list fall out of the range of analysis. To address these issues, we devised a scalable, dictionary-based method to automatically detect lexical gender that can provide a dynamic, up-to-date analysis with high coverage. Our approach reaches over 80% accuracy in determining the lexical gender of nouns retrieved randomly from a Wikipedia sample and when testing on a list of gendered words used in previous research.

Courtney Ford, Ojas Rane, Susan Leavy

Navigating AI regulation across jurisdictions is increasingly difficult for policymakers, legal professionals, and researchers. To address this, we present a multi-jurisdictional Retrieval-Augmented Generation system for global AI regulation. Our corpus includes 242 documents across 68 jurisdictions, ranging from formal legislation like the EU AI Act to unstructured policy documents such as national AI strategies. The system makes three technical contributions: type-specific chunking that preserve legal structure across heterogenous documents; conditional retrieval routing with entity detection and metadata for legal citations; and priority-based re-ranking to boost enacted legislation over policy and secondary sources. Evaluation of 50 queries reveals strong performance across both single-entity and multi-jurisdictional questions, achieving 0.87 average faithfulness and 0.84 average answer relevancy. Single-entity queries achieve 0.86 average faithfulness and 0.92 average answer relevancy, while multi-jurisdictional comparison queries achieve 0.88 average faithfulness and 0.75 average answer relevancy. These findings highlight the effectiveness of domain-specific retrieval strategies for navigating complex, heterogenous regulatory corpora.

Susan Leavy

Recommender systems are becoming increasingly central as mediators of information with the potential to profoundly influence societal opinion. While approaches are being developed to ensure these systems are designed in a responsible way, adolescents in particular, represent a potentially vulnerable user group requiring explicit consideration. This is especially important given the nature of their access and use of recommender systems but also their role as providers of content. This paper proposes core principles for the ethical design of recommender systems and evaluates whether current approaches to ensuring adherence to these principles are sufficiently inclusive of the particular needs and potential vulnerabilities of adolescent users.

Qin Ruan, Jin Xu, Ruihai Dong et al.

Societal risk emanating from how recommender algorithms disseminate content online is now well documented. Emergent regulation aims to mitigate this risk through ethical audits and enabling new research on the social impact of algorithms. However, there is currently a need for tools and methods that enable such evaluation. This paper presents ARTAI, an evaluation environment that enables large-scale assessments of recommender algorithms to identify harmful patterns in how content is distributed online and enables the implementation of new regulatory requirements for increased transparency in recommender systems.

Yoshua Bengio, Sören Mindermann, Daniel Privitera et al. · eth-zurich, mit

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the report's Chair, these independent experts collectively had full discretion over the report's content.

Marion Bartl, Thomas Brendan Murphy, Susan Leavy

Gender-inclusive language is often used with the aim of ensuring that all individuals, regardless of gender, can be associated with certain concepts. While psycholinguistic studies have examined its effects in relation to human cognition, it remains unclear how Large Language Models (LLMs) process gender-inclusive language. Given that commercial LLMs are gaining an increasingly strong foothold in everyday applications, it is crucial to examine whether LLMs in fact interpret gender-inclusive language neutrally, because the language they generate has the potential to influence the language of their users. This study examines whether LLM-generated coreferent terms align with a given gender expression or reflect model biases. Adapting psycholinguistic methods from French to English and German, we find that in English, LLMs generally maintain the antecedent's gender but exhibit underlying masculine bias. In German, this bias is much stronger, overriding all tested gender-neutralization strategies.

Susan Leavy

This paper presents research uncovering systematic gender bias in the representation of political leaders in the media, using artificial intelligence. Newspaper coverage of Irish ministers over a fifteen year period was gathered and analysed with natural language processing techniques and machine learning. Findings demonstrate evidence of gender bias in the portrayal of female politicians, the kind of policies they were associated with and how they were evaluated in terms of their performance as political leaders. This paper also sets out a methodology whereby media content may be analysed on a large scale utilising techniques from artificial intelligence within a theoretical framework founded in gender theory and feminist linguistics.

Susan Leavy, Gerardine Meaney, Karen Wade et al.

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given the complex way gender ideology is embedded in language. This paper proposes a framework for the identification of gender bias in training data for machine learning.The work draws upon gender theory and sociolinguistics to systematically indicate levels of bias in textual training data and associated neural word embedding models, thus highlighting pathways for both removing bias from training data and critically assessing its impact.