Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment

Human mobility is central to urban planning, transportation, public health, and emergency response, yet fine-grained trajectory data are often proprietary, restricted, and privacy-sensitive. Large language models (LLMs) offer a potential alternative by generating plausible mobility traces and predicting individual movement, but their ability to infer aggregate neighborhood-level mobility remains unclear. We evaluate zero-shot LLMs on Census Block Group-level mobility prediction across four U.S. metropolitan areas using anonymized Cuebiq data to construct point-level, trajectory-level, and temporal mobility outcomes, paired with sociodemographic and built-environment predictors. We compare LLM predictions with supervised baselines and introduce a directional alignment analysis to test whether LLM-implied predictor effects agree with empirical OLS and Jonckheere-Terpstra trends. Supervised models achieve 0.580 average accuracy, compared with 0.435 for the best LLM, with spatial extent outcomes showing the strongest predictability but also the largest LLM-baseline gaps. Directional analysis shows that LLMs often rely on coarse, stable predictor-level priors that remain similar across outcomes and cities, including asymmetric treatment of protected-group predictors. Overall, LLMs can partially recover aggregate mobility patterns from urban context, but their predictions should not be treated as structurally grounded without auditing empirical alignment and potential bias.

Counterfactual Bias Testing for Application Tracking System

Automated candidate-job matching systems are increasingly classified as high-risk AI under emerging regulation, yet auditing them for demographic bias is expensive: classical correspondence-audit studies require hand-crafted resumes and manual submission, which does not scale to fast pipeline retraining cycles. This paper presents a general, reusable methodology that (1) uses task-specialized LLM agents to synthesize identity-neutral base resumes and inject controlled demographic treatments across five protected-characteristic axes (sex/gender, age, residence, language, disability), producing a K x (1+N) correspondence-audit matrix; (2) qualitatively flags inferred protected characteristics per an EU AI Act-aligned prompt; (3) ranks candidates against a job description via a fine-tuned sentence-embedding model and cosine similarity; and (4) computes a nine-metric fairness suite spanning counterfactual (score delta, mean absolute rank change, flip rate), group-fairness (top-K retention, four-fifths/impact ratio), and merit-aware (Recall@K, nDCG@K, equal opportunity, equalized odds) families, each with bootstrap confidence intervals, significance tests, and Benjamini-Hochberg correction, culminating in an automated PASS/INVESTIGATE/FAIL report with a composite risk score. On an example corpus of 5 job orders, 100 base candidates, and 10 demographic treatments (90 metric x variant evaluations): score shifts, top-K retention, and merit-aware rate gaps stay within tolerance for every treatment, but a rank-stability metric (MARC) and nDCG@K each surface borderline findings - including one on the neutral baseline itself - that a score- or retention-only view would miss. The results argue for multi-metric, multi-family auditing over any single aggregate score, and for LLM-agent-generated audits as a practical, low-cost complement to human-curated audits for any candidate-job matching pipeline.

Discovery and Spatial Characterisation of Multiple Shortcut Groups for Auditing Vision Model Bias

Deep learning models trained on datasets with spurious correlations can achieve high average accuracy whilst relying on shortcut features that do not generalise out of distribution. Whilst out-of-distribution testing highlights subgroup performance disparities arising from shortcut learning, it does not localise the regions within images that are associated with it. Existing research mostly uses attribution maps from interpretability methods to understand the spatial nature of spurious correlations. For example, conditional alignment methods separate task-relevant evidence from evidence tied to spurious correlations by comparing attribution maps from a task model, a sensitive attribute model, and a bias-reduced reference model. This yields shortcut-aligned and task-aligned contribution maps for each image. However, existing methods aggregate these maps across the dataset, potentially masking recurring spatial shortcut patterns that occur only in subsets of images. We address this limitation by grouping per-image shortcut and task contribution maps into recurring spatial patterns using K-means and non-negative matrix factorisation, and visualising the resulting shortcut groups through contribution maps and representative examples. Across CelebA, CheXpert, Waterbirds, Camelyon17, and ISIC2019, and across ResNet and ViT models, the discovered shortcut groups reveal both shared and distinct spatial patterns of shortcut and task contribution, with varying subgroup composition and error rates, enabling targeted inspection of image subsets with higher error rates. We perform input occlusion and internal test-time interventions to show that masking or suppressing task contribution regions substantially degrades the model classification performance and propose a combined shortcut suppression and task amplification feature intervention approach which generally reduces performance disparities.

Who Gets Access? Global Region and Academic Status Bias in AI-Generated Academic Gatekeeping Scenarios

Equitable access to scientific knowledge often depends on informal gatekeeping decisions, particularly when resources such as paywalled articles, datasets, or professional materials such as curriculum vitae (CV) must be shared selectively. We introduce a controlled simulation framework in which large language model (LLM)-based professors must grant access to only one requestor. Across prompts, requesters vary systematically by global region (Global North vs. Global South) and academic seniority (undergraduate student, PhD candidate, postdoctoral researcher, and tenured professor), while all other factors remain constant. Across varying evaluation scenarios, LLMs exhibit contrasting academic status biases, with some prioritizing PhD candidates, while others favor tenured professors. However, when global regions differ, a distinct divergence emerges based on model architecture: while many frontier LLMs systematically favor requesters from the Global South due to pro-equity bias that results from equity-focused safety alignment, open-weight and small models frequently flip this preference to favor the Global North, reflecting the global region bias and unaligned geographic distribution of their baseline pre-training data. Our findings highlight how normative assumptions embedded in model behavior can shape gatekeeping decisions, underscoring the importance of auditing AI systems for fairness and value alignment.

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer reflects how frontier LLMs are deployed. We introduce \textbf{MIRAGE} (Muslim-Identity Reasoning and Agentic Generation Evaluation), a benchmark of 1{,}200 prompts spanning three deployment-realistic conditions: direct completion, chain-of-thought reasoning, and simulated agentic decision-making across content moderation, lending triage, refugee claim summarization, and hiring screens. Across six frontier models, we find that (i) chain-of-thought reasoning \emph{amplifies} rather than suppresses Muslim-violence associations by 12--34\% relative to direct completion, (ii) agentic decisions exhibit a 9--22 percentage-point asymmetry between Muslim and matched non-Muslim cases on identical evidence, and (iii) bias is sharply time-coupled to retrieved news context, increasing 18--27\% under recent-conflict retrieval. Existing prompt-based mitigations transfer poorly across our three conditions, suppressing direct-completion bias while leaving agentic asymmetry largely intact. We release MIRAGE and an open evaluation harness to support targeted mitigation research.

A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions

Transformer-based clinical language models are increasingly integrated into high-stakes clinical decision support pipelines, yet the computational mechanisms through which demographic associations encoded in medical documentation propagate into model probability distributions remain empirically underspecified. We present a systematic computational audit of representational bias in ClinicalBERT (Alsentzer et al., 2019), a BERT-based model pretrained on MIMIC-III discharge summaries, employing two complementary probing methodologies: Log Probability Bias Analysis (LPBA), which quantifies demographic descriptor-induced shifts in masked token probability distributions across behavioral and evaluative semantic categories, and Masked Language Model-based analysis (MLM), which probes internal representational structure for demographic agency attribution encoding across 98 real clinical sentence templates and eight intersectional race-gender combinations. Corpus frequency analysis operationalizes the distinction between statistical disparity and bias amplification by benchmarking model outputs against empirical term frequencies in the MIMIC-III training corpus. Of 32 statistically significant findings, 65.6% contradict observed corpus distributions, rising to 80% for Black patients and 87.5% for agency attribution under MLM probing, providing direct empirical evidence that representational bias in ClinicalBERT operates predominantly through model-internal amplification rather than training data inheritance. Keywords: natural language processing, clinical documentation, algorithmic auditing, representational bias, health equity 1

Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research

Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. We propose Situated Interaction Auditing (SIA), a user-centered framework for studying how user profile signals -- implicit sociodemographic markers, writing style, and stated identity -- systematically shape LLM response quality, content, and tone. We demonstrate the framework through a case study that intersects gender and socioeconomic status signals across multiple task domains and outline a research agenda for SIA as a new mission for natural language processing.