New papers on fairness, safety, alignment and governance.

Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms that promote novelty and diversity. In practice, the strength of such interventions is typically controlled using global hyperparameters, fixed regularization weights, heuristic caps, or offline tuning strategies. These approaches implicitly assume that a single level of exploration is appropriate across users, contexts, and stages of interaction. I

Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect implicit biases, which carry weak associations with many social demographics and cannot extend to dimensions like age or socioeconomic status. We introduce ImplicitBBQ, a QA benchmark that evaluates implicit bias through characteristic based cues, culturally assoc

Dyslexic spelling errors exhibit systematic phonological and orthographic patterns that distinguish them from the errors produced by typically developing writers. While this observation has motivated dyslexic-specific spell-checking and assistive writing tools, prior work has focused predominantly on error correction rather than attribution, and has largely neglected the ethical risks. The risk of harmful labelling, covert screening, algorithmic bias, and institutional misuse that automated clas

In agentic systems, human-generated data records anchor the value of AI services. Yet cloud compute pipelines centralize processing on remote servers. Data centralization reduces personal data sovereignty and may potentially degrade the quality of service (QoS). Meanwhile, user contributions are diverse in quantity and quality: decentralized records can be biased, noisy, and heterogeneously distributed. To address the data challenge, we study fair token allocation and private data valuation for

Popularity bias is a pervasive problem in recommender systems, where recommendations disproportionately favor popular items. This not only results in "rich-get-richer" dynamics and a homogenization of visible content, but can also lead to misalignment of recommendations with individual users' preferences for popular or niche content. This work studies popularity bias through the lens of user-recommender alignment. To this end, we introduce Popularity Quantile Calibration, a measurement framework

Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. We propose the Dignified Peer framework, which counters servility with anti-sycophancy and trustworthiness, and mitigates evasiveness through empathy and creativity. Realizing this agent requires overcoming significant challenges in data supervision, objective collapse, and evaluation bias. We addr

Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open essay-scoring datasets (ASAP 2.0, ELLIPSE, and DREsS) that cover both holistic and analytic scoring. We analyze agreement with human consensus scores, directional bias, and the stability of bias estimates. Our results show that strong open-weight models achieve modera

Skin cancer, particularly melanoma, remains a major cause of morbidity and mortality, making early detection critical. AI-driven dermatology systems often rely on skin lesion segmentation as a preprocessing step to delineate the lesion from surrounding skin and support downstream analysis. While fairness concerns regarding skin tone have been widely studied for lesion classification, the influence of skin tone on the segmentation stage remains under-quantified and is frequently assessed using co

Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generativ

Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal consequences. Despite high reported accuracy, growing evidence demonstrates that such systems often exhibit uneven performance across demographic groups, leading to disproportionate error rates and potential harm. This paper argues that aggregate accuracy is an insufficient metric for evaluating the fairness and reliability of facial recognitio

Despite there now being more than 1,000 FDA-authorised AI medical devices, formal equity assessments -- whether model performance is uniform across patient subgroups -- are rare. Here, we evaluate the equity of 18 open-source brain tumour segmentation models across 648 glioma patients from two independent datasets (n = 11,664 model inferences) along distinct univariate, Bayesian multivariate, spatial, and representational dimensions. We find that patient identity consistently explains more perfo

While powerful in image-conditioned generation, multimodal large language models (MLLMs) can display uneven performance across demographic groups, highlighting fairness risks. In safety-critical clinical settings, such disparities risk producing unequal diagnostic narratives and eroding trust in AI-assisted decision-making. While fairness has been studied extensively in vision-only and language-only models, its impact on MLLMs remains largely underexplored. To address these biases, we introduce

Speech Emotion Recognition (SER) systems have growing applications in sensitive domains such as mental health and education, where biased predictions can cause harm. Traditional fairness metrics, such as Equalised Odds and Demographic Parity, often overlook the joint dependency between demographic attributes and model predictions. We propose a fairness modelling approach for SER that explicitly captures allocative bias by learning the joint relationship between demographic attributes and model e

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle, formalizing supervised learning as a problem of optimal two-part lossless compression. Our theory explains how simplicity bias governs feature selection in neural networks through a fundamental trade-off between model complexity (the cost of describing the hypothesis

Multimodal Large Language Models (MLLMs) have recently been explored as face verification systems that determine whether two face images are of the same person. Unlike dedicated face recognition systems, MLLMs approach this task through visual prompting and rely on general visual and reasoning abilities. However, the demographic fairness of these models remains largely unexplored. In this paper, we present a benchmarking study that evaluates nine open-source MLLMs from six model families, rangin

Alzheimer's disease (AD) is a growing global health challenge as populations age, and timely, accurate diagnosis is essential to reduce individual and societal burden. However, real-world AD assessment is hampered by incomplete, heterogeneous multimodal data and variability across sites and patient demographics. Although large language models (LLMs) have shown promise in biomedicine, their use in AD has largely been confined to answering narrow, disease-specific questions rather than generating

Recent research points toward LLMs being manipulated through adversarial and seemingly benign inputs, resulting in harmful, biased, or policy-violating outputs. In this paper, we study an underexplored issue concerning harmful and toxic mathematical word problems. We show that math questions, particularly those framed as natural language narratives, can serve as a subtle medium for propagating biased, unethical, or psychologically harmful content, with heightened risks in educational settings in

Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving

Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper. While this focuses on the most directly relevant text, it prevents relative comparisons across all the works a paper cites. We propose Crystal, which instead jointly ranks all cited papers within a citing paper using large language models (LLMs). To mitigate LLMs' positional bias, we rank each list three times in a randomized order and aggregate the impact labels through maj

One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. Models optimized for this definition are typically evaluated on how well demographic attributes can be classified given model representations, with the (implicit) assumption that this measure accurately reflects \textit{recommendation parity}, i.e., how similar recommendations given to different users are. We challenge this assumption by

Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly optimize supervised and unsupervised objectives and achieve promising results. However, inherent optimization interference still limits their ability to improve further. Through quantitative analysis, we identify a key issue, i.e., gradient entanglement, which 1) distorts supervised gradients and weakens discrimination among known classes, and 2

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external documents that are relevant to the user's query. However, relatively little work has investigated the impact of RAG in terms of fairness. Particularly, it is not yet known if queries that are associated with certain groups within a fairness category systematically receive higher accuracy, or accuracy improvements in RAG system

RLHF-aligned language models exhibit response homogenization: on TruthfulQA (n=790), 40-79% of questions produce a single semantic cluster across 10 i.i.d. samples. On affected questions, sampling-based uncertainty methods have zero discriminative power (AUROC=0.500), while free token entropy retains signal (0.603). This alignment tax is task-dependent: on GSM8K (n=500), token entropy achieves 0.724 (Cohen's d=0.81). A base-vs-instruct ablation confirms the causal role of alignment: the base mod

HandOver (HO) control in cellular networks is governed by a set of HO control parameters that are traditionally configured through rule-based heuristics. A key parameter for HO optimization is the Cell Individual Offset (CIO), defined for each pair of neighboring cells and used to bias HO triggering decisions. At network scale, tuning CIOs becomes a tightly coupled problem: small changes can redirect mobility flows across multiple neighbors, and static rules often degrade under non-stationary tr

Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging diffusion models and real-world scenarios. However, existing diffusion inversion methods often suffer from low reconstruction quality or weak robustness. Two major challenge

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and over extended interactions, phenomena like opinion drift, over-alignment, and confirmation bias start to matter a lot. BeliefShift introduces a longitudinal benchmark designed specifically to evaluate belief dynamics in multi-session LLM interactions. It covers

Ethical discourse on AI in healthcare has focused predominantly on back-end concerns such as bias, fairness and explainability, while the front-end interface, where patients and clinicians actually encounter AI outputs, remains under explored. This paper identifies imbalanced user-AI relationships as a distinct class of front-end ethical failure: patients are rendered highly visible to AI systems through data inference, yet cannot understand, question or influence how they are represented. Throu

We present PopResume, a population-representative resume dataset for causal fairness auditing of LLM- and VLM-based resume screening systems. Unlike existing benchmarks that rely on manually injected demographic information and outcome-level disparities, PopResume is grounded in population statistics and preserves natural attribute relationships, enabling path-specific effect (PSE)-based fairness evaluation. We decompose the effect of a protected attribute on resume scores into two paths: the bu

The proliferation of Generative Artificial Intelligence has transformed benign cognitive offloading into a systemic risk of cognitive agency surrender. Driven by the commercial dogma of "zero-friction" design, highly fluent AI interfaces actively exploit human cognitive miserliness, prematurely satisfying the need for cognitive closure and inducing severe automation bias. To empirically quantify this epistemic erosion, we deployed a zero-shot semantic classification pipeline ($τ=0.7$) on 1,223 h

Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We report three findings that challenge prevailing assumptions about how these systems process and integrate visual information. First, Frontier models readily generate detailed image descriptions and elaborate reasoning traces, including pathology-biased clinical findings, for images never provided; we

Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based steering, and causal interventions, often act at a single stage of the pipeline, resulting in incomplete mitigation and brittle utility trade-offs under distribution shifts. We propose CatRAG Debiasing, a dual-pronged framework that integrates functor with Retrieval

We identify first-mover bias -- path-dependent concentration of SHAP feature importance from sequential residual fitting in gradient boosting -- as a mechanistic contributor to attribution instability under multicollinearity. Scaling up a single model amplifies this effect: a Large Single Model matching our method's total tree count produces the poorest attribution reproducibility of any approach tested. We show that model independence largely neutralizes first-mover bias. Both DASH (Diversified

Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory. The vectors are updated online from weak scalar rewa

Food security policy formulation in data-scarce regions remains a critical challenge due to limited structured datasets, fragmented textual reports, and demographic bias in decision-making systems. This study proposes ZeroHungerAI, an integrated Natural Language Processing (NLP) and Machine Learning (ML) framework designed for evidence-based food security policy modeling under extreme data scarcity. The system combines structured socio-economic indicators with contextual policy text embeddings u

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-ho

Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models are highly sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples. In this paper, we provide a rigorous mathematical formalization of the ``Bias Manifold'' within the FM framework. We

Many works in the literature show that LLM outputs exhibit discriminatory behaviour, triggering stereotype-based inferences based on the dialect in which the inputs are written. This bias has been shown to be particularly pronounced when the same inputs are provided to LLMs in Standard American English (SAE) and African-American English (AAE). In this paper, we replicate existing analyses of dialect-sensitive stereotype generation in LLM outputs and investigate the effects of mitigation strategi

The rapid evolution of artificial intelligence, from task-specific systems to foundation models exhibiting broad, flexible competence across reasoning, creative synthesis, and social interaction, has outpaced the conceptual and governance frameworks designed to manage it. Current regulatory paradigms, anchored in a tool-centric worldview, address algorithmic bias and transparency but leave unanswered foundational questions about what increasingly capable synthetic minds are, how societies should

Large language models (LLMs) based AI systems increasingly mediate what billions of people see, choose and buy. This creates an urgent need to quantify the systemic risks of LLM-driven market intermediation, including its implications for market fairness, competition, and the diversity of information exposure. This paper introduces ChoiceEval, a reproducible framework for auditing preferences for brands and cultures in large language models (LLMs) under realistic usage conditions. ChoiceEval add

Large language models are increasingly used to support organizational decisions from hiring to governance, raising fairness concerns in AI-assisted evaluation. Prior work has focused mainly on demographic bias and broader preference effects, rather than on whether evaluators reward expressed trust in AI itself. We study this phenomenon as LLM Nepotism, an attitude-driven bias channel in which favorable signals toward AI are rewarded even when they are not relevant to role-related merit. We intro