New papers on fairness, safety, alignment and governance.

In 3D scene understanding, deep learning models rely on large models and extensive training to capture basic geometric structures that are present in the 3D data. However, existing methods lack explicit mechanisms to incorporate geometric information, such as learnable primitive shapes, often necessitating large models and more training data which in turn increases cost and can limit generalization. We introduce GIBLy, a lightweight geometric inductive bias layer that integrates learnable geomet

Since 2019, medical societies have reconsidered race-specific clinical equations often in parallel to and largely independent from algorithmic fairness research. Focusing on lung function reference algorithms that affect medical care, insurance, and employment for hundreds of millions globally, we analyze the transition from race-specific GLI-2012 to race-averaged GLI-Global through a fairness lens. Drawing on historical context, citation analysis, and quantitative evaluation, we show (i) limite

It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We tested seven open-weight LLM pairs consisting of the base model (pre-training only) and the chat model (pre-training and post-training) from seven labs on a paired-scenario forced-choice probe over 28 country pairs in English, French, and Chinese, and found that geopolitical bias originates in post-training rather than in pre-training. Across seven AI l

A central question in computational vision is whether human-like visual representations are better explained by discriminative or generative learning. Existing comparisons, however, often confound the learning objective with architecture, scale, and training data, leaving open whether the objective itself drives alignment. We address this confound using Joint Energy-Based Models (JEMs), which interpolate continuously between discriminative and generative training within a fixed architecture. By

Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional mult

We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1) Signal:} We propose that Platonic alignment arises from the universal relationship between objects and attributes, which is encoded linearly in representations according to the Linear Representation Hypothesis (LRH). We provide evidence that LRH helps explain PRH by extracting linear object-attribute features with sparse autoencoders and showing

Large language models exhibit a risk-averse "turtle" bias as strategic agents. We show that injecting a symbolic reasoning framework as a per-round reflective prompt into one agent acts as a small perturbation whose consequences are not per-decision but emergent: the agent's risk posture is unchanged in isolation, yet over a campaign of accumulating memory and multi-agent interaction the conditions settle into distinct, condition-associated winner ecosystems. In a 7-player Warring States Diploma

AI-enabled services deployed in critical digital infrastructure are subject to governance obligations spanning transparency, accountability, fairness, and traceability. Compliance today remains documentation-centric: obligations are described in prose, audits rely on static checklists, and verification depends on manual review. Such approaches do not scale to automated AI systems. This paper introduces Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles re

Assessing the spatial fairness of predictive models involves establishing whether they are statistically penalizing (favoring) individuals associated with certain geographical locations. Literature on this topic makes the fundamental assumption that each individual is assigned to a single geographical location (e.g., place of residence). However, fairness with respect to the set of locations where one has been, i.e., their movement patterns over different regions, also matters when fairness is c

Empirical claims about autonomous Kubernetes operations agents are largely unfalsifiable. Published work reports observational results without controlled comparisons against an agent-disabled baseline, selection bias is endemic, pre-registered decision matrices are absent, and samples are typically too small for the noise level of the underlying scoring system. The cause is the same gap that limits the agents themselves: code agents have a verification substrate that turns "did it work" into a f

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve fa

Vehicle-to-vehicle (V2V) energy trading enables decentralized peer-to-peer energy exchange among electric vehicles (EVs), reducing grid dependency while monetizing surplus capacity. However, coordinating self-interested EV agents with diverse charging needs and uncertain arrival-departure schedules remains challenging. Existing approaches either require centralized optimization with computational limitations or lack fairness guarantees. This paper integrates Nash Bargaining Solution into Multi-A

Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached even when the current visual state has substantially diverged from them, while discarding potentially more relevant intermediate history. As a result, the retained long-range context may become less adaptive and bias generation toward outd

Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach. However, existing evaluations primarily focus on changes in LLM benchmark performance, providing limited insight into whether apparent bias reductions reflect meaningful changes in a model's internal mechanisms. In this work, we investigate how CoT prompting affects

Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-based systems. Inspired by neural coupling in human communication, we study how such models coordinate their internal representations during interaction. We simulate full-duplex dialogues between two instances of the pretrained \textit{Moshi} model under controlled conditions, manipulating channel noise and decoding bias. Synchronization is measured

Social roles shape expectations, priorities, and judgments, yet it remains unclear how large language models (LLMs) associate occupational identities with broader cultural value patterns. Prior work used nationality-based cultural prompting to study how LLM responses to value-survey questions align with human cultural benchmarks. In this paper, we extend that framework by replacing cultural prompting with occupational prompting to examine how professional-role cues influence value-survey respons

Explainable AI (XAI) is often criticized for failing to satisfy broad desiderata (e.g., fairness, accountability) and for limited practical value to stakeholders. This challenge partly arises because researchers across disciplines prioritize different sets of desiderata that remain underspecified and context-dependent, yet expect XAI to satisfy them simultaneously, resulting in fragmented and sometimes incompatible operationalizations. We argue that many desiderata are not independent, but inste

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-l

For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images, but the alignment procedure requires value function estimates at noisy intermediate latents. Existing methods resort to Tweedie-style or Monte Carlo approximations, trading off estimator bias against computational cost: Tweedie estimates are efficient but bias

LLM-agent simulation offers a flexible computational tool for studying population response trajectories that depend on scenario events, memory, demographics, and evolving social context. However, full multi-round simulation scales linearly with both population size and horizon, requiring every agent to query the LLM at every round. We propose Adaptive Prototype Simulation (APS), a framework that reframes scalable LLM-based simulation as a recurrent oracle-allocation problem. APS retains the desi

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label Noise via Mimetic Bias, where rewards prioritize statistical likelihood over logical truth, creating a "correctness illusion" that masks compounding errors; (2) Coarse-Grained Supervision, where sparse global outcomes (e.g., in GRPO) fail to provide granular gui

Artificial Intelligence (AI) is transforming higher education (HE) through personalised learning, predictive analytics, and intelligent automation. However, concerns over algorithmic bias, privacy, and inequity necessitate governance models that prioritise Human Intelligence (HI). This study introduces the Human-Driven AI in Higher Education (HD-AIHED) framework, which embeds stakeholder-driven HI, particularly in decision-making and feedback across all five AI lifecycle phases: adoption (multi-

Constrained machine learning enables fairness-aware training, physics-informed neural networks, and integration of symbolic domain knowledge into statistical models. Despite its practical importance, no general method exists for the non-convex, non-smooth, stochastic setting that arises naturally in deep learning. We propose the Stochastic Penalty-Barrier Method (SPBM), which extends classical penalty and barrier methods to this setting via exponential dual averaging, a stabilized penalty schedu

Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database. We show that an attacker can poison the database by injecting a small number of crafted music captions, causing the system to retrieve malicious captions that bias prompt augmentation and steer generation away from the user's intended function, without modifying the user prompt, r

Cities are increasingly turning to large-scale data analysis and machine learning to make consequential decisions. While the algorithmic fairness community has focused on analyzing the risks and benefits associated with these complex methods, there has been much less scrutiny of the many simpler, but still widely used, data-driven tools that support government decision-making in a variety of settings. In this work, we study hand-crafted indices for geographic targeting and decision-making in eme

Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under non-IID data distributions, SFL often suffers from biased optimization and unstable convergence, while existing solutions largely adapt techniques from conventional federated learning. In this work, we observe that the split architecture of SFL inherently alters how client information is represented and coordinated, opening opportunities for bias co

Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias benchmarks remain useful, but they do not show how models frame newly emerging events for different prompted audiences. We introduce GPF-LIVENEWS, a streaming evaluation protocol and benchmark snapshot for auditing group-conditioned framing in open-ended LLM outputs. The protocol expands fresh BBC/Reuters news anchors ac

LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three families show high call accuracy but much lower no-call accuracy, leaving overall accuracy in the 55%-70% range. We trace this to an Intrinsic Bias Hypothesis (IBH): the call/no-call decision mapping carries an activation-independent call offset, so the model favors call even at activation parity. Using Sparse Autoencoders (SAEs), we rec

Mortgage lending in the United States exhibits persistent racial and gender disparities. We investigate whether standard data preprocessing steps, specifically attribute binning, amplify these disparities in downstream pattern mining. Using 103,481 cleaned mortgage applications from the HMDA 2023 dataset (Chicago metropolitan area), we build a three-stage pipeline: (1) a PySpark data cleaning and binning pipeline that implements both standard equal-frequency binning and the epsilon-biased fair b

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and Distinguishable Refusal (DR), which steers models away from using sensitive knowledge during inference. Despite rapid progress, KD-based unlearning struggles with biased deletion due to suppressing specific token sequences as a substitute for complete knowledge removal, w

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinations, stereotypes, and socially biased content. In particular, LLMs are prone to prejudiced responses involving race, gender, and age, which are collectively referred to as social biases. Prior studies have used fine-tuning and prompt engineering to mitigate such biases in LLMs,

Root cause analysis (RCA) in microservices is challenging due to (i) noisy and heterogeneous multimodal observability (metrics, logs, traces), (ii) cascading failure propagation that amplifies downstream symptoms, and (iii) non-stationary topology drift induced by autoscaling and rolling updates. Recent LLM-based RCA agents can generate tool-grounded explanations, yet they often remain topology-agnostic and suffer from \emph{symptom-amplification bias}, misattributing the root cause to salient d

Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabular fair SSL through a diagnostic stress test: under confidence-gated pseudo-labeling, moment-matching fairness regularizers can trigger two failure modes -- Masking Collapse (fairness erodes confidence, starving pseudo-labels) and Trivial Saturation (drift to constant predictors

Financial, social, and political factors often prevent the interests of the owners of ML systems and services and their users from being perfectly aligned. ML systems often produce biased information that can influence users to make decisions that are not in their best interest. Current solution approaches require ML systems to implement protocols to mitigate their biases. However, ML system owners usually do not have any incentive to implement these protocols and often argue that it limits thei

Large-scale facial datasets like CelebA are widely used in computer vision, yet the cultural biases embedded in their labels remain underexplored. Fairness research has distinguished representational from allocational harms, but audits of computer vision datasets have mostly examined categorical labels, leaving open how such harms appear in learned features and model attention. This paper examines CelebA at three levels: dataset structure, learned feature weights, and spatial attention, focusing

Machine learning (ML) algorithms are increasingly deployed in high-stakes decision-making domains such as loan approvals, hiring, and recidivism predictions. While existing fairness metrics (e.g., statistical parity, equal opportunity) effectively quantify outcome-oriented disparities, they offer limited insight into the procedure or explanation behind biased decisions. To address this gap, we propose Group-level Explanation Stability Disparity (GESD), a \textit{procedural-oriented} fairness met

Algorithmic fairness research often assumes a tradeoff between fairness and accuracy. Yet this tradeoff may not be universal. We test this assumption in the context of U.S. property tax assessment - a setting in which the output of predictive algorithms directly determines the distribution of tax obligations among homeowners. Currently, systematic assessment errors cause owners of lower-valued properties to face disproportionately high tax burdens, creating regressivity in the property tax syste

The ability of a small set of coordinated actors to manipulate opinions in online social networks poses a serious challenge to the fairness and integrity of public debate. We investigate this problem by studying how targeted stubborn agents can shift the average opinion of a network governed by the Hegselmann-Krause bounded-confidence dynamics. Experiments are conducted on weighted LFR benchmark networks with community structure, using multiple node-selection strategies based on degree, strength

Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decisive visual cues that appear sparsely across sequences, and from inadequate modeling of multi-scale temporal dynamics, as short-term discriminative cues and long-range dependencies are often either ove

Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting to be integrated into higher-impact pipelines. Since generated images tend to reinforce stereotypes, producing representational erasure via "default" depictions and shaping perceptions of who belongs in certain roles, a growing body of work has proposed metrics to quantify gender bias in T2I outputs. Yet existing evaluations remain fragmented. Met