AI ethics on Wednesday, 18 March 2026

Language models encode task-relevant knowledge in internal representations that far exceeds their output performance, but whether mechanistic interpretability methods can bridge this knowledge-action gap has not been systematically tested. We compared four mechanistic interpretability methods -- concept bottleneck steering (Steerling-8B), sparse autoencoder feature steering, logit lens with activation patching, and linear probing with truthfulness separator vector steering (Qwen 2.5 7B Instruct)

Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information ("zombie memories") from contaminating the context window. We introduce MemArchitect, a governance layer that decouples memory lifecycle management from model weights. MemArchitect enforces explicit, rule-based poli

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce targeted behavioral changes. However, such conclusions are typically drawn under relatively relaxed evaluation settings that overlook deployment constraints, capability trade-offs, and real-world robustness. We therefore introduce \textbf{FaithSteer-BENCH}, a

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

Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability. In contrast, benchmarks validating health-related large language models (LLMs) rarely characterize the "patient" or "query" populations they contain. Without defined composition, aggregate performance metrics may misrepresent model readiness for clinical use. Methods: We analyzed 18,707 consumer health queries across six public benchmarks using LLMs as automated coding instruments to apply a standardiz

Out-of-distribution (OOD) detection is essential for deploying deep learning models reliably, yet no single method performs consistently across architectures and datasets -- a scorer that leads on one benchmark often falters on another. We attribute this inconsistency to a shared structural limitation: logit-based methods see only the classifier's confidence signal, while feature-based methods attempt to measure membership in the training distribution but do so in the full feature space where co

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We study political censorship in Chinese-origin language models as a natural experiment, using probes, surgical ablations, and behavioral tests across nine open-weight models from five labs. Three findings follow. First, probe accuracy alone is non-diagnostic: politi

Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally expensive and memory intensive, limiting its deployment in resource-constrained environments. This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected dense 3x3 convolutional layers with structured low-rank separable convolutions, trained e

Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training stability. However, DPO suffers from the recently identified squeezing effect (also known as likelihood displacement), where the probability of preferred responses decreases unintentionally during training. To understand and mitigate this phenomenon, we develop a theoretical framework that models the coordinate-wise dyn

Current artificial intelligence systems struggle with systematic compositional reasoning: the capacity to recombine known components in novel configurations. This paper argues that the failure is architectural, not merely a matter of scale or training data, and that its origins lie in the psychological learning theories from which AI paradigms were derived. The argument proceeds in three stages. First, drawing on the systematicity debate in cognitive science and on the demonstration of Aizawa th

Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constructing machine-checkable proofs, a task that remains beyond current automation. We propose a hierarchical proof search framework for automated code verification in Lean~4 that decomposes complex verification goals into structurally simpler subgoals before attempting tactic-level proving. Central to our approach is a pr

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misalignment. We introduce VLM-AutoDrive, a modular post-training framework for adapting pretrained Vision

Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades undetected, downstream decisions lose their grounding in the exchange that produced them. Yet current evaluation methods assess isolated outputs rather than the interaction producing them. Here we show that conversational structural consistency can be monitored dir

Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input representations with geometric cues rather than explicitly teaching models to reason in 3D space. We introduce Loc3R-VLM, a framework that equips 2D Vision-Language Models with advanced 3D understanding capabilities from monocular video input. Inspired by human spatial co

The CARE Workshop on Robotics and AI in Medicine, held on December 1, 2025 in Indianapolis, convened leading researchers, clinicians, industry innovators, and federal stakeholders to shape a national vision for advancing robotics and artificial intelligence in healthcare. The event highlighted the accelerating need for coordinated research efforts that bridge engineering innovation with real clinical priorities, emphasizing safety, reliability, and translational readiness with an emphasis on the

Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, making it attractive for efficient inference. However, many practical conversion baselines rely on weight-only low-rank approximations (e.g., SVD-style initializations) and uniform rank allocation. They focus on minimizing the difference between weight matrices rather than on how those weights affect input activations, ign

As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages remains poorly understood. We present the first systematic evaluation of LLM safety across 12 Indic languages, spoken by over 1.2 billion people but underrepresented in LLM training data. Using a dataset of 6,000 culturally grounded prompts spanning caste, religion, gender, health, and politics, we assess 10 leading LLMs on translated variants of the prompt.

In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications. Concretely, we study the narrative-to-play task: inferring stage-play layouts (scenes, speaker positions, movements, and room types) from text that lacks explicit spatial, positional, or relational cues. We then introduce a dramaturgy-inspired deterministic evaluation suite and, fina

Background: Amid the opportunities and risks introduced by generative AI, learning research needs to envision how human minds and responsibilities should re-adapt as AI augments or automates various tasks and enters daily learning, knowledge work, and social life. Approach: Drawing on theories of learning, intelligence, and knowledge creation, this conceptual paper proposes intellectual stewardship as a human-centered, conceptually grounded framework for advancing creative learning practices wit

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control comm

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory silos across agent workflows; governance fragmentation across teams and tools; unstructured memories unusable by downstream systems; redundant context delivery in autonomous multi-step executions; and silent quality degradation without feedback loops. We pres

Automated radiology report generation has gained increasing attention with the rise of deep learning and large language models. However, fully generative approaches often suffer from hallucinations and lack clinical grounding, limiting their reliability in real-world workflows. In this study, we propose a multimodal retrieval-augmented generation (RAG) system for grounded drafting of chest radiograph impressions. The system combines contrastive image-text embeddings, case-based similarity retrie

Dark humor often relies on subtle cultural nuances and implicit cues that require contextual reasoning to interpret, posing safety challenges that current static benchmarks fail to capture. To address this, we introduce a novel multimodal, multilingual benchmark for detecting and understanding harmful and offensive humor. Our manually curated dataset comprises 3,000 texts and 6,000 images in English and Arabic, alongside 1,200 videos that span English, Arabic, and language-independent (universal

As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more pronounced when aligning multiple, potentially conflicting human values. Although recent approaches, such as reward reweighting, prompt-based supervised fine-tuning, and model merging, attempt to tackle multi-value alignment, they still face two major limitations:

In the real economy, modern decision-making is fundamentally challenged by high-dimensional, multimodal environments, which are further complicated by agent heterogeneity and combinatorial data sparsity. This paper introduces a Multi-Agent Large Language Model-based Economic Sandbox (MALLES), leveraging the inherent generalization capabilities of large-sacle models to establish a unified simulation framework applicable to cross-domain and cross-category scenarios. Central to our approach is a pr

We present a practical, reproducible framework for identifying undervalued football players grounded in objective mispricing. Instead of relying on subjective expert labels, we estimate an expected market value from structured data (historical market dynamics, biographical and contract features, transfer history) and compare it to the observed valuation to define mispricing. We then assess whether news-derived Natural Language Processing (NLP) features (i.e., sentiment statistics and semantic em

Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important re

Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity

The rapid adoption of generative artificial intelligence (AI) in educational assessment has created new opportunities for scalable item creation, personalized feedback, and efficient formative evaluation. However, despite advances in taxonomy alignment and automated question generation, the absence of transparent, explainable, and certifiable mechanisms limits institutional and accreditation-level acceptance. This chapter proposes a comprehensive framework for explainability and certification of

We present an agent-driven approach to the construction of parameter inference pipelines for scientific data analysis. Our method leverages a multi-agent system, Cmbagent (the analysis system of the AI scientist Denario), in which specialized agents collaborate to generate research ideas, write and execute code, evaluate results, and iteratively refine the overall pipeline. As a case study, we apply this approach to the FAIR Universe Weak Lensing Uncertainty Challenge, a competition under time c

In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not limited to incorrect final outputs. They also arise from long-horizon interaction, stochastic decisions, and external side effects (such as API calls, database writes, and message sends). Common failures include non-termination, role drift, propagation of unsupp

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

In this paper, we introduce a novel kinematics-rich vision-language-action (VLA) task, in which language commands densely encode diverse kinematic attributes (such as direction, trajectory, orientation, and relative displacement) from initiation through completion, at key moments, unlike existing action instructions that capture kinematics only coarsely or partially, thereby supporting fine-grained and personalized manipulation. In this setting, where task goals remain invariant while execution

Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing safety benchmarks remain fragmented across tasks and modalities, limiting the comprehensive evaluation of complex system-level vulnerabilities. To address this gap, we introduce UniSAFE, the first comprehensive benchmark for system-level safety evaluation of UMMs across 7 I/O modality combinations, spanning conventional t

Unsupervised Domain Adaptation (UDA) seeks to transfer knowledge from a labeled source domain to an unlabeled target domain but often suffers from severe domain and scale gaps that degrade performance. Existing cross-attention-based transformers can align features across domains, yet they struggle to preserve content semantics under large appearance and scale variations. To explicitly address these challenges, we introduce the concept of beneficial noise, which regularizes cross-attention by inj

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision signals, providing complementary semantic context. However, hand-crafted textual descriptions struggle to capture the inherent visual diversity of individuals across scenes, limiting the model's ability to learn scene-aware representations. To address this chall

This article introduces and substantiates the concept of Neuro-Linguistic Integration (NLI), a novel paradigm for human-technology interaction where Large Language Models (LLMs) act as a key semantic interface between raw neural data and their social application. We analyse the dual nature of LLMs in this role: as tools that augment human capabilities in communication, medicine, and education, and as sources of unprecedented ethical risks to mental autonomy and neurorights. By synthesizing insig

Current Large Language Models (LLMs) are gradually exploited in practically valuable agentic workflows such as Deep Research, E-commerce recommendation, and job recruitment. In these applications, LLMs need to select some optimal solutions from massive candidates, which we term as \textit{LLM-as-a-Recommender} paradigm. However, the reliability of using LLM agents for recommendations is underexplored. In this work, we introduce a \textbf{Bias} \textbf{Rec}ommendation \textbf{Bench}mark (\textbf{

The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexical similarity. The contrastive learning paradigm is fundamentallya static representation consolidation technique: during training, it encodes hier-archical relevance concepts into fixed geometric structures in the vector space,and at inference time it cannot dynamically adjust relevance judgments accord-ing to the spec

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success rates. In this paper, we observe that VLMs can clearly distinguish benign inputs from harmful ones in their representation space. Moreover, even among harmful inputs, jailbreak samples form a distinct internal state that is separable from refusal samples. These

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper, we reveal that LRMs' safety degradation occurs only after CoT is enabled, and this degradation is not observed when CoT is disabled. This observation motivates us to consider encouraging LRMs to make safety decisions before CoT generation. To this end, we propo

Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These limitations severely hinder agents from internalizing latent decision dynamics and generalizing effectively. Moreover, practical adaptation is often impeded by the prohibitive resource and time costs associated with standard training paradigms. To overcome these challe

The foundation model era -- roughly 2020 to 2025 -- is over. The forces that defined it have inverted. Open source models have reached frontier performance while inference costs approach zero, exposing what was always structurally true: pre-training large language models at scale is not a durable competitive moat. The US government's formal designation of Anthropic as a supply chain risk in February 2026 accelerated a transition already underway -- but did not cause it. The paper argues that the

The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. Although Multimodal LLMs offer a promising paradigm, they fundamentally struggle to bridge the gap between general visual semantics and rigorous evidentiary protocols, often leading to perceptual hall

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate

Story visualization requires generating sequential imagery that aligns semantically with evolving narratives while maintaining rigorous consistency in character identity and visual style. However, existing methodologies often struggle with subject inconsistency and identity drift, particularly when depicting complex interactions or extended narrative arcs. To address these challenges, we propose a cohesive two-stage framework designed for robust and consistent story generation. First, we introdu

Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks including sentiment analysis and event extraction to acting as dynamic decision-making agents in complex financial environments. However, the evolution of LLMs into autonomous financial agents faces a significant dilemma in evaluation paradigms. Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static benchmarks are often confin

Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transparent evaluation. We present \textbf{CentaurTA Studio}, a web-based system for self-improving human--agent collaboration in open coding and theme construction. The system integrates (1) a two-stage human feedback pipeline separating simulator drafting and expert validation, (2) persistent prompt optimization that distills validated feedback into reus

Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric dat

Online discussions of science involve complex interactions among experts, news media, and social media users as they interpret and disseminate scientific findings. While prior work has examined these actors in isolation, their interplay in shaping science communication remains poorly understood. Using the COVID-19 pandemic as a case study, we analyze 1.24M tweets and 211k news articles that reference pandemic-related scientific papers. We find that the most influential Twitter accounts in this d

Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via

This document is a peer review by Go Kian Tik — GKT (Mbah Hogi Bejo™) of Meriel B.’s 10-day research series. Meriel B. is an AI Ethics Researcher, AI Governance Specialist, and founder of AI.MIRROR. Her research covers ten domains: the global AI governance crisis (Day 1), structural AI bias against women (Day 2), ML-based child criminality prediction (Day 3), the collapse of voluntary compliance in a military context (Day 4), LinkedIn’s algorithmic bias (Day 5), AI hallucination on non-Latin scr

This document is a peer review by Go Kian Tik — GKT (Mbah Hogi Bejo™) of Meriel B.’s 10-day research series. Meriel B. is an AI Ethics Researcher, AI Governance Specialist, and founder of AI.MIRROR. Her research covers ten domains: the global AI governance crisis (Day 1), structural AI bias against women (Day 2), ML-based child criminality prediction (Day 3), the collapse of voluntary compliance in a military context (Day 4), LinkedIn’s algorithmic bias (Day 5), AI hallucination on non-Latin scr