AI ethics on Friday, 6 March 2026

Mindfulness meditation is a widely accessible and evidence-based method for supporting mental health. Despite the proliferation of mindfulness meditation apps, sustaining user engagement remains a persistent challenge. Personalizing the meditation experience is a promising strategy to improve engagement, but it often requires costly and unscalable manual effort. We present MindfulAgents, a multi-agent system powered by large language models that (1) generates guided meditation scripts based on a

The remarkable reasoning and code generation capabilities of large language models (LLMs) have recently motivated increasing interest in automating formal verification (FV), a process that ensures hardware correctness through mathematically precise assertions but remains highly labor-intensive, particularly through the translation of natural language into SystemVerilog Assertions (NL-to-SVA). However, LLMs still struggle with SVA generation due to limited training data and the intrinsic complexi

The agentic web marks a structural transition from a human-centered information network to a digital environment populated by artificial intelligence (AI) agents that perceive, decide, and act autonomously. As delegated action unfolds at machine speed, exceeds discrete moments of human judgment, and distributes decision-making across non-human actors, existing legal frameworks face growing strain, creating an urgent need for new mechanisms capable of sustaining legality in this emerging order. A

Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire increased agency and human oversight diminishes. In this work, we present LieCraft: a novel evaluation framework and sandbox for measuring LLM deception that addresses key limitations of prior game-based evaluations. At its core, LieCraft is a novel multiplayer hidden-role game in which players select an ethical alignment

Discovering compact governing equations from experimental observations is one of the defining objectives of quantitative science, yet practical discovery pipelines routinely fail when measurements are noisy, relevant state variables are unobserved, or multiple symbolic structures explain the data equally well within statistical uncertainty. Here we introduce SymLang (Symmetry-constrained Language-guided equation discovery), a unified framework that brings together three previously separate ideas

Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful capability uplift: the marginal increase in a user's ability to cause harm with a frontier model beyond what conventional tools already enable. We frame harmful capability uplift as a core AI safety metric, ground it in prior social science research, and provide concre

The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic deception, manipulation, and reward-seeking, that can arise despite safety training. Gaining a mechanistic understanding of these failures requires empirical approaches that can isolate behavioral patterns in controlled settings. We propose that biological mis

Inference-time alignment effectively steers large language models (LLMs) by generating multiple candidates from a reference model and selecting among them with an imperfect reward model. However, current strategies face a fundamental dilemma: ``optimistic'' approaches like Best-of-$N$ suffer from reward hacking, while ``pessimistic'' regularized methods often stifle the exploration needed to discover high-quality responses. In this work, we formalize this trade-off through the lens of regret min

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans' ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based

We present LiveSense - a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into a centimeter-level Range-Doppler sensor while preserving simultaneous communication capability. The laptops are equipped with COTS Intel AX211 (Wi-Fi 6E) or Intel BE201 (Wi-Fi 7) NICs. LiveSense can (i) Extract fully-synchronized channel state information (CSI) at >= 40 Hz, (ii) Perform time-phase alignment and self-interference cancellation on-device, and

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from labeled examples, while methods that better extract these signals require hundreds to thousands of examples. We introduce COLD-Steer, a training-free framework that steers LLM activations by approximating the representational changes that would result from gradi

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural lan

As autonomous agents increasingly operate in real-world digital ecosystems, understanding how they coordinate, form institutions, and accumulate shared culture becomes both a scientific and practical priority. This paper introduces TerraLingua, a persistent multi-agent ecology designed to study open-ended dynamics in such systems. Unlike prior large language model simulations with static or consequence-free environments, TerraLingua imposes resource constraints and limited lifespans for the agen

Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output achieves only 20.0 degrees -- a 3.3x bottleneck. LoRA fine-tuning (r=16, 2,000 images) narrows this gap to 6.5 degrees, providing evidence for a pathway-training deficit rather than a representational one. Training objective determines accuracy more than architecture: five encoders

Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model is adapted to learn early stopping at specified content boundaries when provided with limited future text. During inference,

Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse medical imaging tasks. Because annotation campaigns produce a growing stream of task-specific labelled data, online adaptation of the segmentation model is a natural complement to zero-shot inference. We propose CLoPA, a continual adaptation strategy that tunes a small fraction of nnInteractive's parameters on the ann

Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are difficult to guarantee when an LLM decides what runs. Semi-structured interviews with 18 experts across 10 industrial R&D stakeholders surface 2 competing requirements--deterministic, constrained execution and conversational flexibility without workflow rigidity--together with boundary properties (human-in-

Foundation models such as Segment Anything Model 3 (SAM3) enable flexible text-guided medical image segmentation, yet their predictions remain highly sensitive to prompt formulation. Even semantically equivalent descriptions can yield inconsistent masks, limiting reliability in clinical and pathology workflows. We reformulate prompt sensitivity as a group-wise consistency problem. Semantically related prompts are organized into \emph{prompt groups} sharing the same ground-truth mask, and a promp

AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review with large language models often suffers from uneven coverage, weak reproducibility, unsupported findings, and the absence of an immutable audit trail. The ESAA architecture addresses a related governance problem in agentic software engineering by separating

Large-scale biomedical vision-language models (VLMs) adapted on high-end imaging (e.g., CT) often fail to transfer to frontline low-end modalities (e.g., radiography), collapsing into modality-specific shortcuts. We propose K-MaT (Knowledge-Anchored Manifold Transport), a prompt-learning framework that transfers decision structures to low-end modalities without requiring low-end training images. K-MaT factorizes prompts, anchors them to clinical text descriptions, and aligns the low-end prompt m

Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We introduce SAHOO, a practical framework to monitor and control drift through three safeguards: (i) the Goal Drift Index (GDI), a learned multi-signal detector combining semantic, lexical, structural, and distributional measures; (ii) constraint preservation checks that enforce safety-critical invariants

Physics-Informed Neural Networks (PINNs) enforce governing equations by penalizing PDE residuals at interior collocation points, but standard collocation strategies - uniform sampling and residual-based adaptive refinement - can oversample smooth regions, produce highly correlated point sets, and incur unnecessary training cost. We reinterpret collocation selection as a coreset construction problem: from a large candidate pool, select a fixed-size subset that is simultaneously informative (high

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally expensive or lack calibration. We propose a three-stage pipeline to post-train LLMs to efficiently infer calibrated uncertainty estimates for their responses. First, we compute fine-grained entropy-based uncertainty scores on the training data, capturing the distr

When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We observe that this degradation is related to the deterioration of cross-modal information structure, where dependencies among visual observations, language instructions, and actions progressively diffuse during continual adaptation. But existing continual learning methods fail to preserve such cross-modal information dep

The quadratic computational complexity of self-attention remains a fundamental bottleneck for scaling Large Language Models (LLMs) to long contexts, particularly during the pre-filling phase. In this paper, we rethink the causal attention mechanism from the perspective of information flow. Due to causal constraints, tokens at initial positions participate in the aggregation of every subsequent token. However, existing sparse methods typically apply a uniform top-k selection across all token posi

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and synthesize it into structured reports before answer selection. Although such pipelines can improve performance, their impact on reliability under model variability remains unclear. In real-world deployment, heterogeneous models may align, diverge, or synchroni

Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present a comprehensive, multilingual audit of the cultural alignment of contemporary LLMs including GPT-4o-Mini, Gemini-2.5-Flash, Llama 3.2, Mistral and Gemma 3 across India, East Asia and Southeast Asia. Our study specifically focuses

Recent years have seen rapid growth in the market for HR technology and AI-driven HR solutions in particular. This popularity has also resulted in increased attention to the negative aspects of using AI to support hiring practices, such as the risk of reinforcing existing biases against vulnerable groups based on gender or other sensitive attributes. Combining human experience with AI efficiency in making recruiting and selection decisions has the potential to help mitigate these biases, but des

Trajectory prediction is essential for autonomous driving, enabling vehicles to anticipate the motion of surrounding agents to support safe planning. However, most existing predictors assume fixed-length histories and suffer substantial performance degradation when observations are variable or extremely short in real-world settings (e.g., due to occlusion or a limited sensing range). We propose TaPD (Temporal-adaptive Progressive Distillation), a unified plug-and-play framework for observation-a

Multimodal Summarization (MMS) aims to generate concise textual summaries by understanding and integrating information across videos, transcripts, and images. However, existing approaches still suffer from three main challenges: (1) reliance on domain-specific supervision, (2) implicit fusion with weak cross-modal grounding, and (3) flat temporal modeling without event transitions. To address these issues, we introduce **CoE**, a training-free MMS framework that performs structured reasoning thr

Universities are microcosms of urban ecosystems, with concentrated consumption patterns in food, transport, energy, and product usage. These environments not only contribute substantially to sustainability pressures but also provide a unique opportunity to advance sustainability education and behavioural change at scale. As in most sectors, digital sustainability initiatives within universities remain narrowly focused on carbon calculations, typically providing static feedback that limits opport

We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety. Unlike prior metrics, CRIMSON incorporates full clinical context, including patient age, indication, and guideline-based decision rules, and prevents normal or clinically insignificant findings from exerting disproportionate influence on the overall score. The framework categorizes errors into a compreh

The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as strong alternatives to conventional diffusion models. At the same time, inference-time enhancement strategies have been shown to improve the generation quality and text-prompt alignment of text-to-image diffusion models. However, these techniques are mainly a

Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability properties such as solubility, thermostability, and expression. Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets, yet they are target dependent and demand substantial domain expertise or careful hyperparameter tuning. In this paper, we introduce ProtAlign, a

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards: smaller subsets represent simpler policies, which can be learned more reliably because their empirical gradient estimates are more accurate. Our approach allows for modeling and comparison of different policy classes, including full planning, greedy, K-step loo

This report presents a structured Robotics Physical Safety Framework based on explicit asset declaration, systematic vulnerability enumeration, and hazard-driven synthetic data generation. The approach bridges classical risk engineering with modern machine learning pipelines, enabling safety envelope learning grounded in a formalized hazard ontology. The key contribution of this framework is the alignment between classical safety engineering, digital twin simulation, synthetic data generation, a

While explainable AI (XAI) is often heralded as a means to enhance transparency and trustworthiness in closed-loop neurotechnology for psychiatric and neurological conditions, its real-world prevalence remains low. Moreover, empirical evidence suggests that the type of explanations provided by current XAI methods often fails to align with clinicians' end-user needs. In this viewpoint, we argue that clinically meaningful explainability (CME) is essential for AI-enabled closed-loop medical neurote

General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions. In contrast, instruction-tuned embedders can align embeddings with textual instructions yet cannot autonomously infer latent corpus structures, such as determining the optimal number of clusters. To address both limitations, we reframe instruction-following clustering as a generative task and train large reasoning models (LRMs) as autonomous

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect audio-visual alignment under challenging speech conditions. This paper introduces TempoSyncDiff, a reference-conditioned latent diffusion framework that explores few-step inference for efficient audio-driven talking-head generation. The approach adopts a teache

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models often fail on simple visual questions that are highly relevant to automated driving, and the reasons behind these failures remain poorly understood. In this work, we examine the intermediate activations of VLMs and assess the extent to which specific visual concep

Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced institutions. While Decentralized Diffusion Models (DDM) enable training multiple experts in isolation, existing approaches require 1176 GPU-days and homogeneous training objectives across all experts. We present an efficient framework that dramatically reduces resource requirements while supporting heterogeneous training o

Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configured execution environment, which requires resolving complex software dependencies, aligning hardware and framework versions, and configuring distributed execution, yet this capability remains largely unbenchmarked. We introduce ResearchEnvBench, a benchmark for environment synthesi

In conversational search systems, a key component is to determine and clarify the intent behind complex queries. We view intent clarification in light of the exploratory search paradigm, where users, through an iterative, evolving process of selection, exploration and retrieval, transform a visceral or conscious need into a formalized one. Augmenting the clarification component with a retrieval step (retrieval-augmented intent clarification) can seriously enhance clarification performance, espec

Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across variables. Existing ISTS forecasting methods often solely utilize historical observations to predict future ones while falling short in learning contextual semantics and fine-grained temporal patterns. To address these problems, we achieve MM-ISTS, a multimodal framework augmented by vision-text large language models, that bridges temporal, visual, a

The explosion of big social data has created a scalability trap for traditional qualitative research, as manual coding remains labor-intensive and conventional topic models often suffer from semantic thinning and a lack of domain awareness. This paper introduces Textual Hybrid Embedding based Topic Analysis (THETA), a novel computational paradigm and open-source tool designed to bridge the gap between massive data scale and rich theoretical depth. THETA moves beyond frequency-based statistics by

Change captioning generates descriptions that explicitly describe the differences between two visually similar images. Existing methods operate on static image pairs, thus ignoring the rich temporal dynamics of the change procedure, which is the key to understand not only what has changed but also how it occurs. We introduce ProCap, a novel framework that reformulates change modeling from static image comparison to dynamic procedure modeling. ProCap features a two-stage design: The first stage t

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capab

This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level similarity, under the assumption that backdoor-triggered generations exhibit strong consistency across samples. However, they struggle to generalize to recently emerging backdoor attacks, where backdoored generations can appear visually diverse. BlackMirror is motivate

Credit risk scoring must support high-stakes lending decisions where data distributions change over time, probability estimates must be reliable, and group-level fairness is required. While modern machine learning models improve default prediction accuracy, they often produce poorly calibrated scores under distribution shift and may create unfair outcomes when trained without explicit constraints. This paper proposes Calibrated Credit Intelligence (CCI), a deployment-oriented framework that comb

Differences in data distributions between demographic groups, known as the problem of infra-marginality, complicate how people evaluate fairness in machine learning models. We present a user study with 85 participants in a hypothetical medical decision-making scenario to examine two treatments: group-specific model performance and training data availability. Our results show that participants did not equate fairness with simple statistical parity. When group-specific performances were equal or u

Although organizations increasingly position AI adoption as a pathway to competitiveness and innovation, organizations' perspectives on productivity and efficiency often clash with workers' perspectives on AI's economic and social value. Through design workshops with 15 UX designers, we examine how AI adoption unfolds across individual, team, and organizational scales. At the individual level, designers weighed efficiency, skill development, and professional worth. At the team level, they negoti

Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why a model refuses a request, nor intervene when its safety judgments fail. We propose Safe Transformer, a modular approach that augments pre-trained language models by inserting a discrete information bottleneck containing an explicit safety bit between transformer layers. The safety bit serves as both an interpretable signal of the model's safety c

Trust plays a pivotal role in enabling effective cooperation, reducing uncertainty, and guiding decision-making in both human interactions and multi-agent systems. Although it is significant, there is limited understanding of how large language models (LLMs) internally conceptualize and reason about trust. This work presents a white-box analysis of trust representation in EleutherAI/gpt-j-6B, using contrastive prompting to generate embedding vectors within the activation space of the LLM for dia

Large Language Models (LLMs) are transforming Conversational Visual Analytics (CVA) by enabling data analysis through natural language. However, evaluating LLMs for CVA remains a challenge: requiring programming expertise, overlooking real-world complexity, and lacking interpretable metrics for multi-format (visualizations and text) outputs. Through interviews with 22 CVA developers and 16 end-users, we identified use cases, evaluation criteria and workflows. We present Lexara, a user-centered e

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate speech" or "incitement"; hiring managers may use LLMs to rank who counts as "qualified"; and AI labs increasingly train models to self-regulate under constitutional-style ambiguous principles such as "biased" or "legitimate". This paper introduces ambiguity collapse

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and structure separately, limiting the ability to exploit the alignment between the structure and protein sequence embeddings. In this paper, we introduce a sequence structure contrastive alignment framework, which learns a shared embedding space where proteins are repres

Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the \textbf{\underline{D}}isentangled \textbf{\underline{S}}afety \textbf{\underline{H}}ypothesis \textbf{(DSH)}, positing that safety computation operates on two distinct subspaces: a \textit{Recognition Axis} ($\mathbf{v}_H$, ``Knowing'') and an \textit{Execution Axi

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing attacks operate primarily at shallow levels, such as the prompt or embedding level, and often fail to expose vulnerabilities rooted in deeper model components, which creates a false sense of security for successful defense. In this paper, we propose \textbf{\underli

Client intake, information retrieval, document assembly, and litigation assistance, among other legal functions, have seen deployment of Artificial Intelligence legal chatbots in legal care delivery. With substantial legal efficiency and access to justice improvements, these tools also pose major legal, ethical, and liability risks. Unlike other legal technologies, legal chatbots lie at the crossroads of the practice of law, consumer protection and automation; oversight of which can have negativ