arXiv subjects

Salima Jaoua

Publications and source records attributed to Salima Jaoua.

4 recordsLinked to original sources

arXiv2026

Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems

Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single pipeline, so they cannot tell where the bias originates. We introduce WORLDVIEW, a multilingual benchmark of 8,960 prompts across 15 languages and 31 language-context pairings. Using it, we audit the revision layer in three systems (DALL-E-3, Imagen-4, GPT-Image-1.5) through a three-step analysis of how heavily it marks each cultural context, whether it flattens that context into a narrow vocabulary, and whether that vocabulary is stereotypical. Relative to a no-context English baseline, the US is the least-marked context, while non-Western and non-Anglophone contexts are marked far more heavily, flattened into narrow vocabularies applied across topically diverse prompts, and reduced to recognizable cultural stereotypes. Comparing images from original versus revised prompts on models without a revision layer, we identify the layer itself as a previously undocumented, causal source of this stereotyping. To locate cultural bias, and fix it, we must audit the system as deployed, not the model alone.

cs.AI↗

arXiv2026

A scalable Bayesian functional factor model for high-dimensional longitudinal molecular data

Large-scale longitudinal molecular profiling is now firmly established in biomedical research, prompted by the need to uncover coordinated biomarker trajectories reflecting the dynamics of underlying biological mechanisms and characterise patient heterogeneity in disease progression. While a range of statistical tools exist for either longitudinal modelling or high-dimensional analysis, there is no unified framework tailored to address these questions jointly. Motivated by a longitudinal COVID-19 study conducted in Cambridge hospitals, we propose a Bayesian functional factor model to address this gap. The framework combines latent factor modelling with functional principal component analysis to represent shared temporal programmes across subsets of variables while capturing individual variation through low-dimensional functional scores. We specify sparsity-inducing priors that yield interpretable factor structure and allow the effective number of factors to be inferred via overspecification. An annealed variational algorithm ensures efficient joint posterior inference at scale. The approach achieves accurate recovery of temporal structure in simulations with up to 20 000 variables. Application to the COVID-19 data reveals clinically meaningful heterogeneity in recovery dynamics through interpretable subject-level scores capturing coordinated inflammatory and immune-response pathway activity. The methodology is implemented in the R package bayesSYNC.

stat.ME↗

arXiv2025

The Order of Recommendation Matters: Structured Exploration for Improving the Fairness of Content Creators

Social media platforms provide millions of professional content creators with sustainable incomes. Their income is largely influenced by their number of views and followers, which in turn depends on the platform's recommender system (RS). So, as with regular jobs, it is important to ensure that RSs distribute revenue in a fair way. For example, prior work analyzed whether the creators of the highest-quality content would receive the most followers and income. Results showed this is unlikely to be the case, but did not suggest targeted solutions. In this work, we first use theoretical analysis and simulations on synthetic datasets to understand the system better and find interventions that improve fairness for creators. We find that the use of ordered pairwise comparison overcomes the cold start problem for a new set of items and greatly increases the chance of achieving fair outcomes for all content creators. Importantly, it also maintains user satisfaction. We also test the intervention on the MovieLens dataset and investigate its effectiveness on platforms with interaction histories that are currently unfair for content creators. These experiments reveal that the intervention improves fairness when deployed at early stages of the platform, but the effect decreases as the strength of pre-existing bias increases. Altogether, we find that the ordered pairwise comparison approach might offer a plausible alternative for both new and existing platforms to implement.

cs.CY↗

arXiv2025

Visibility Allocation Systems: How Algorithmic Design Shapes Online Visibility and Societal Outcomes

Throughout application domains, we now rely extensively on algorithmic systems to engage with ever-expanding datasets of information. Despite their benefits, these systems are often complex (comprising of many intricate tools, e.g., moderation, recommender systems, prediction models), of unknown structure (due to the lack of accompanying documentation), and having hard-to-predict yet potentially severe downstream consequences (due to the extensive use, systematic enactment of existing errors, and many comprising feedback loops). As such, understanding and evaluating these systems as a whole remains a challenge for both researchers and legislators. To aid ongoing efforts, we introduce a formal framework for such visibility allocation systems (VASs) which we define as (semi-)automated systems deciding which (processed) data to present a human user with. We review typical tools comprising VASs and define the associated computational problems they solve. By doing so, VASs can be decomposed into sub-processes and illustrated via data flow diagrams. Moreover, we survey metrics for evaluating VASs throughout the pipeline, thus aiding system diagnostics. Using forecasting-based recommendations in school choice as a case study, we demonstrate how our framework can support VAS evaluation. We also discuss how our framework can support ongoing AI-legislative efforts to locate obligations, quantify systemic risks, and enable adaptive compliance.

cs.CY↗