New papers on fairness, safety, alignment and governance.

arXiv:2607.26062v1 Announce Type: new Abstract: Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intellectual disabilities (ID). Objective: The study aims to identify and measure representational differences related to people with ID and examine them to identify implicit biases inherent in AI chat generation technologies. Methods: Utilizing the GPT-4-Turbo model, we requested story-generation based on

arXiv:2502.10605v4 Announce Type: replace-cross Abstract: Problem definition: Estimating causal effects of interventions is central to policy and operations, but outcome data are often missing or costly to obtain. LLMs can provide text annotation at scale but may be subject to unknown bias. When ground-truth outcomes require expensive expert labeling or follow-up, budget limits typically allow only a fraction of the data to be labeled. Motivated by collaboration with a nonprofit conducting stree

Text-to-image (T2I) workflows are increasingly deployed on serverless platforms because users often compose customized workflows and invoke them intermittently. Existing platforms typically deploy each workflow as an opaque GPU function, provisioning, placing, and scaling all constituent models in the workflow together. This monolithic design obscures workflow structure, inflates scaling overhead, forces users to manage low-level GPU coordination, and limits fine-grained fairness in multi-tenant

Resource allocation across multiple agent groups arises in many applications including e-commerce recommendation systems, housing assignment, and course allocation, and is commonly formulated as an optimization problem with diversity constraints to ensure group fairness. Existing approaches typically enforce these constraints as hard conditions, which overly restrict the feasible solution space and often lead to suboptimal allocations. In this paper, we propose PRA, a parameterized framework for

Publication date: September 2026 Source: Technology in Society, Volume 88 Author(s): Paloma Almodóvar, Alberto Ferraris

arXiv:2607.25425v1 Announce Type: cross Abstract: Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web exploitation, and binary exploitation. Large language models (LLMs) can now solve a growing share of challenges with minimal human input, raising urgent questions about fairness, the validity of rankings, and whether participation still delivers the learning that justifies the effort. This paper report

arXiv:2507.11548v3 Announce Type: replace Abstract: The use of publicly available generative AI systems for resume evaluation is often justified by the assumption that these tools reduce bias relative to human judgment. However, this framing leaves a prior question unresolved: whether these systems are capable of performing the evaluative task at all. This study presents a two-part audit of eight widely used AI platforms used for resume screening. Drawing on the concept of the Illusion of Neutra

arXiv:2508.05775v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. Meanwhile, they pose risks by inadvertently producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for text generation and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey

Reliable fault detection in multi-robot systems requires models capable of capturing complex, time-dependent fault signatures that manifest over extended temporal horizons rather than instantaneous observations alone. Existing data-driven approaches operate reactively on behavioural snapshots, failing to capture fault modes whose discriminative signature depends on temporally ordered precursors. This work formalises a theoretical impossibility result demonstrating that memoryless classifiers are

Positive quadratic networks admit the low-rank representation f_U(x)=x^top UU^top x, where Uinmathbb{R}^{dtimes r} is identifiable only up to right orthogonal multiplication, representing a rank-r PSD matrix Q=UU^top. We study how this quotient structure governs training dynamics, curvature, recovery, and interpolation bias. On the full-column-rank stratum, we identify mathbb{R}^{dtimes r}_*/O(r) with the rank-r PSD manifold. For smooth objectives L(U)=ell(UU^top), the Euclidean factor gradient

Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web exploitation, and binary exploitation. Large language models (LLMs) can now solve a growing share of challenges with minimal human input, raising urgent questions about fairness, the validity of rankings, and whether participation still delivers the learning that justifies the effort. This paper reports a mixed-methods study of LLM impact on modern CT

India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recognized languages. Large language models (LLMs) are now being deployed on a massive scale throughout the mainland as well as in remote villages. However, the common benchmarks - MMLU, BIG-Bench, and TruthfulQA are almost exclusively English- and Western-centric. They do not identify those safety, fairness, and accuracy failures unique to the Indian co

arXiv:2607.23539v1 Announce Type: new Abstract: AI agents can transact online on behalf of a human principal---browsing, paying, receiving, and reviewing---without linking a transaction to a principal. That architecture starves algorithmic discrimination of its inputs---identity, purchase history, location history, behavioral traces, and demographic proxies---but also forecloses its proof. Disparate-treatment needs comparators; disparate-impact needs protected-class baselines; and Iqbal-era plea

arXiv:2607.24275v1 Announce Type: cross Abstract: Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory requirements and system-level verification. This challenge is particularly acute in digital phenotyping, where continuous behavioural data raises concerns around consent, privacy, and fairness. In this paper, we propose a computational ethical framework for AI-driven digital phenotyping system in whi

arXiv:2407.14766v4 Announce Type: replace-cross Abstract: This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability and transparency of corrective methods, and on the opposition between two fairness criteria, namely Demographic Parity and Equalized Odds. Our main argument is that even as a gap in Demographic Parity is used to diagnose inequality between groups, Equalized Odds constitutes a more reliable fairness crit

Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines s

Big Data & Society, Volume 13, Issue 3, July-September 2026. The COVID-19 pandemic witnessed the transformation of data from a public health resource into a measure of morality. Disadvantage indices such as the Healthy Places Index and other metrics became central to promoting equity in the pandemic response, ...

Empirical user studies are essential for evaluating visual encodings and can reveal perceptual and cognitive mechanisms, but they do not by themselves provide causal, predictive accounts of interpretation errors. Evaluations are therefore often post hoc: they measure performance after a design has been specified rather than predicting how attention, uncertainty, memory, and bias may produce accurate or erroneous judgments. To address this mechanistic gap, we translate a cognitive theory of visua

Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspected before targets are found. This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM). We compare a ground-measured SVC signature, a fully informed in-scene c

Glioma grading from tumor contours is often treated as a pixel problem even when the signal of interest is shape. We align closed contours with a functional shape-alignment framework, separate global deformation from residual Fourier shape, and organize these quantities as frequency-ordered tokens. In five-fold patient-disjoint cross-validation on BraTS~2020 tumor contours, with model selection performed using grouped inner validation, a compact multilayer perceptron (MLP) achieves the highest m

Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without relying on labeled data. Existing methods, such as GAEs, have demonstrated effectiveness but typically rely on message-passing mechanisms that assume homophily, leading to performance degradation on heterophilous graphs, where connected nodes exhibit dissimilar features. This homophily bias results in the loss of critical high-frequency components th

arXiv:2604.00024v2 Announce Type: replace-cross Abstract: Large language models are increasingly used for medical guidance, but women's health remains under-evaluated in benchmark design. We present the Women's Health Benchmark (WHBench), a targeted evaluation suite of 47 expert-crafted scenarios across 10 women's health topics, designed to expose clinically meaningful failure modes including outdated guidelines, unsafe omissions, dosing errors, and equity-related blind spots. We evaluate 22 mod

As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physics or logic constraints. Understanding how training samples in- fluence the model solution (e.g., learned parameters) is crucial for interpretability and robustness. The classical influence function (IF) estimates sample contribu- tions via local sensitivity analysis, measuring how the solution changes when a specific

As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physics or logic constraints. Understanding how training samples in- fluence the model solution (e.g., learned parameters) is crucial for interpretability and robustness. The classical influence function (IF) estimates sample contribu- tions via local sensitivity analysis, measuring how the solution changes when a specific

We study an online variant of discrete fair division under generalized assignment budget constraints. Goods arrive one at a time and must be assigned irrevocably to a feasible agent or to charity, which holds all unallocated goods, while fairness is evaluated only against budget-feasible subsets of every recipient's bundle. We first show that, without additional structure, no deterministic online algorithm can guarantee any fixed approximation to feasible envy-freeness, even in highly symmetric

Publication date: October 2026 Source: Research Policy, Volume 55, Issue 8 Author(s): Wanxiang Cai, Haneul Choi, Tianshu Zhao, Max Munday

Dominant approaches to bias in artificial intelligence (AI) are structured by what I identify as the isolationist problem: the tendency to treat bias as a discrete, technically addressable flaw within the AI development pipeline, rather than as a relational phenomenon embedded in social, institutional, and political arrangements. This problem is sustained by two mutually reinforcing orientations: technocentrism, which reframes ethical challenges as engineering problems amenable to computational

A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral values and spectral subspaces; however, common coordinate-wise rotation-gate data-encoding unitaries used in most quantum machine learning models do not explicitly construct such a matrix-level representation. We introduce Quantum Spectral Mod

Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. These techniques rely on regularization, which prevents representation collapse by enforcing a global target distribution such as a multivariate Gaussian or a uniform distribution on the sphere. However, these global constraints are insufficient to prevent bias entanglement, as task-irrelevant features can still segrega

In this article, we investigate influences of social positionality, designer bias and educational exposure on algorithmic design in healthcare. Against the backdrop of literature on designer bias that points to how it contributes to disproportionate, discriminatory and unethical impacts for racialized and gendered bodies, this study tests this argument with an experiential case study involving Aldebaran’s NAO robot and mechatronics and robotics engineering students at a university in S. E. Ontar

Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data. This makes them especially attractive for auditing models deployed in sensitive domains such as healthcare or finance. For these protocols to be meaningful in real-world audit settings, though, their guarantees must reflect how the model will behave once deployed, rather than merely certifying its behavior during a

Diffusion models typically suffer from error accumulation during iterative sampling, commonly referred to as exposure bias. We reveal systematic frequency-dependent discrepancies between training and inference, which can be interpreted as frequency-dependent SNR error. Crucially, the direction of this mismatch varies across models and timesteps, indicating that fixed correction rules do not generalize. We propose Spectral Alignment (SPA), a lightweight, guidance-based method that calibrates the

Passive sensing for wellbeing uses smartphones and wearables to continuously collect human behavioral data and applies ML/AI models to infer psychological states and behaviors (e.g., depression, cognitive load). These systems are increasingly adopted in high-stakes settings (e.g., hospitals, universities), yet fairness research remains limited---primarily to post-hoc, identity-based comparisons of model performance. However, passive sensing combines heterogeneous sensing infrastructures, indirec

Passive sensing for wellbeing uses smartphones and wearables to continuously collect human behavioral data and applies ML/AI models to infer psychological states and behaviors (e.g., depression, cognitive load). These systems are increasingly adopted in high-stakes settings (e.g., hospitals, universities), yet fairness research remains limited---primarily to post-hoc, identity-based comparisons of model performance. However, passive sensing combines heterogeneous sensing infrastructures, indirec

Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal large language models (MLLMs), prior works fine-tune models on fictitious identities, simulating unlearning requests on subsets of these IDs, which are typically uniformly distributed. However, in realistic scenarios, people from different demographic groups may request to be unlearned at different frequencies, potentiall

Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked. We find its principal side effect is increased bias that standard safety evaluation misses. Holding the model, its training, and the prompts fixed, a quantized model still refuses harmful requests, still avoids over-refusing benign prompts, and still selects the unbiased multiple-choice answer.

arXiv:2607.19389v1 Announce Type: new Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention. In this paper, we revisit the nuances of long-term `fairness' achievable by an ADM, specifically in the context of a credit lending induced wealth process. The literature on long-term fairness mostly (a) considers passive environments, i.e. the outcome of a predictor does not change

arXiv:2607.19586v1 Announce Type: cross Abstract: Despite increasing awareness of cybersecurity risks, users continue to engage in insecure password practices, such as reusing passwords, choosing weak credentials, and neglecting security recommendations. The study explores the behavioral and cognitive factors that influence password decision-making by integrating insights from behavioral economics, particularly hyperbolic discounting, status quo bias, and present bias. We conducted a survey to a

IntroductionQuality control of hatchery production relies on accurate developmental staging of the Pacific white shrimp Litopenaeus vannamei post-larvae (PL), but current methods rely on subjective manual visual evaluation that leads to observer bias and inconsistency.MethodsIn this study, the Hierarchical Isotropic Dense Attention Network (HIDANet) has been introduced, a lightweight convolutional neural network with 0.033M parameters that learns to classify seven post-larval stages (PL5–PL12) i

Human judgment is fundamentally prone to error. A promise of AI is that it will rid decisions of bias and ensure a fairer and safer world for all. Yet research unequivocally demonstrates that LLMs exhibit consequential sociocognitive biases. We alert readers that bias in AI (a) is covert and ironically a feature of alignment goals, (b) is not merely a mirror, but an amplifier of human bias, (c) intensifies across model generations, and (d) even transmits bias to humans. Given the potentially sei