Search arXiv⌕ Search

SEARCH · Search arXiv

Results for “cs.CY”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

7,800 records · Page 6Linked to original sources
arXiv2026

Fairness-Aware Multimodal Transformer Modeling for Real-Time Student Attention Estimation

Automated student-attention estimation can support learning analytics, but aggregate predictive metrics can conceal demographic disparities. This study evaluates fairness-aware multimodal temporal models on DIPSER, a naturalistic classroom dataset combining facial images, wearable-sensor measurements, attention annotations, and automatically inferred demographic metadata. Three baselines are compared across 10 training seeds: a Visual GRU, a Sensor GRU, and a Residual Fusion Transformer. The multimodal model achieves the best mean test performance (MAE 0.283, RMSE 0.363) and the lowest worst-group error among the evaluated baselines, although its gain over the Visual GRU is modest. Gender- and age-targeted MAE-gap regularization reduces disparities on validation data, but these gains do not consistently transfer to held-out subjects or repeated subject-level splits. On an NVIDIA A100-SXM4-40GB GPU, the warm end-to-end pipeline averages 50.65 ms per prediction window at a one-second stride, while the temporal model itself requires 1.02 ms. The findings show that multimodal fusion can modestly improve prediction and worst-group performance, but validation-level fairness gains should not be assumed to generalize. Robust fairness assessment therefore requires subgroup-aware evaluation, repeated subject-level validation, and larger, better balanced demographic samples.

cs.CY↗
arXiv2026

Gurukul AI: An Interactive AI-Driven Educational Platform for Indian Education System

Recent advances in large language models (LLMs) like ChatGPT and LLaMA have transformed AI-driven education, but these systems are predominantly trained on Western-centric data, making them ill-suited for regional curricula like India's. The Indian education system is linguistically diverse, exam-oriented, and structured around standardized syllabi, not addressed by existing datasets or tools. In this work, we curate a syllabus-aligned QA dataset based on NCERT (National Council of Educational Research and Training) textbooks for classes 9-12, capturing the content, context, and teaching style of Indian curricula. The final dataset, comprising 18,720 question-answer pairs across five subjects, is publicly available at https://huggingface.co/datasets/LingoIITGN/Gurukul. We fine-tune the LLaMA 3.1 8B model using this dataset and deploy it in a Retrieval-Augmented Generation (RAG) framework tailored to educational needs. We introduce GurukulAI, an open-access platform that enables Indian students to chat with the model, get doubts cleared, practice exam-style questions, receive contextual answers, and interact in both English and Hindi. By localizing AI for Indian classrooms, our work bridges the gap between global LLM capabilities and regional educational demands. The code is available at https://github.com/lingo-iitgn/GurukulAI.

cs.CL↗
arXiv2026

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations

Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning. Recent work has introduced structured reasoning for multi-turn agent planning and visual QA, decomposing tasks into sequential sub-goals. To extend this to single-shot multimodal social reasoning, we introduce Cognitive Chain-of-Thought (CoCoT), a reasoning framework that structures vision-language-model (VLM) reasoning through three cognitively inspired stages: Perception (extract grounded facts), Situation (infer situations), and Norm (applying social norms). Evaluation across multiple distinct tasks such as multimodal intent disambiguation, multimodal theory of mind, social commonsense reasoning, and safety instruction following, shows consistent improvements (5.9% to 4.6% on average). We further explore the utility of CoCoT for improving models' reasoning through training and show that supervised fine-tuning on CoCoT-structured traces yields 5-6% improvements without explicit CoCoT prompting at inference, demonstrating that models internalize the structured reasoning pattern rather than merely following instructions. We show that structuring model reasoning through cognitively grounded stages enhances interpretability and social alignment, laying the groundwork for more reliable multimodal systems.

cs.CL↗
arXiv2026

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs

LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ

cs.CL↗
arXiv2026

Advisor career stage and PhD advisee outcomes

PhD advisors are central to doctoral training, but their influence may vary across career stages. Early-, mid-, and late-career advisors may differ in research activity, mentoring capacity, professional networks and access to resources. However, little is known about how PhD advisor career stage is associated with PhD student development outcomes. Drawing on multiple large-scale datasets comprising 250,838 advisor-advisee pairs from 312 U.S. PhD-granting institutions, we examine the relationship between advisor career stage and PhD advisee outcomes in knowledge production, collaboration networks and academic career placement. We find that early-career PhD advisors are associated with advisees' higher research productivity and citation performance, more opportunities to engage in direct and intensive research collaboration, and greater likelihood of securing a faculty position. Mid- and late-career faculty, by contrast, appear to have advantages in providing network capital which students can inherit after graduation, training PhD advisees to produce disruptive research, and supporting them in securing faculty positions at top institutions. This study contributes to a more comprehensive understanding of the reproduction of scientific talent by revealing the role of advisor career stage in shaping this process. These findings have implications for doctoral applicants' decision-making and for institutional policymaking on PhD training, faculty support and faculty evaluation.

cs.CY↗
arXiv2026

CompanionSim: Synthetic Data for Evaluating Anthropomorphism in Human-AI Relationships

Many people now see AI systems as not just productivity tools but as social companions. Researchers are eager to study the consequences of AI companionship behaviors, such as validation, which evoke trust, empathy, and attachment in human-human interaction. However, human-AI interaction data is limited and unreliable, slowing research progress. We scale small amounts of real-world data by simulating multi-turn human-chatbot dialogue across a range of chatbot behaviors and use cases. We release CompanionSim: a simulation framework with 2,240 simulated human-chatbot conversations representing 16 chatbot behaviors across seven use cases. Human participants annotated the simulated conversations and real-world conversations in two experiments probing perceptions of companionship behaviors. We conducted Study 1 with a U.S. representative sample ($N_{1}~=~628$) and Study 2 across the U.S., U.K., India, and Nigeria ($N_{2}~=~3,646$). Surprisingly, we find that companionship behaviors reduced likability, humanlikeness, and trust in AI chatbots. These effects were larger in particular subgroups: women and older participants saw companionship chatbots as less likable, humanlike, and trustworthy. We encourage researchers to leverage real-world and synthetic data together to study the differential impacts of AI companions and to create benchmark evaluations of AI chatbots.

cs.CY↗
arXiv2026

Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language Models

We investigate whether Large Language Models (LLMs) exhibit conspiratorial tendencies, whether they display socio-demographic biases in this domain, and how easily they can be conditioned into adopting conspiratorial perspectives. Conspiracy beliefs play a central role in the spread of misinformation and in shaping distrust toward institutions, making them an important testbed for assessing the social and psychological fidelity of LLMs and their potential to reproduce or reinforce harmful narratives. Although LLMs are often used as proxies for studying human behavior, it remains unclear whether they reproduce higher-order psychological constructs such as generalized conspiratorial beliefs. To bridge this research gap, we administer validated psychometric surveys measuring conspiratorial mindset to multiple models under different prompting and conditioning strategies. Our findings reveal that LLMs show partial agreement with elements of conspiracy belief, and conditioning with socio-demographic attributes produces uneven effects, exposing latent demographic biases. Moreover, targeted prompts can easily shift model responses toward conspiratorial directions, underscoring both the susceptibility of LLMs to manipulation and the potential risks of their deployment in sensitive contexts. These results highlight the importance of critically evaluating the psychological dimensions embedded in LLMs, both to advance computational social science and to inform possible mitigation strategies against harmful uses.

cs.CL↗
arXiv2026

Assessing Autonomous Mobility-on-Demand Services and the Impacts of Operational Strategies: A Case Study of Chengdu, China

The Autonomous Mobility-on-Demand (AMoD) service is emerging as a potential alternative to on-demand urban mobility, but its operational performance relative to traditional street-hailing services and the effectiveness of related operational strategies remain unclear. This study presents a simulation framework integrating a graph theory-based trip-vehicle matching mechanism and uses historical street-hailing operations data to simulate AMoD services in Chengdu, China. The operational performance of these two urban mobility modes is evaluated using three key performance indicators: average passenger waiting time (APWT), average deadheading mileage (ADM), and average deadheading energy consumption (ADEC). We further evaluate the impacts of four operational strategies on simulated AMoD performance: vehicle repositioning, fleet size management, geofencing, and request rejection. Simulation results indicate that, under the same historical trip demand, fleet-size constraints, and road network as the observed street-hailing system, the simulated AMoD service is estimated to have lower values of APWT, ADM, and ADEC by 73.3% to 83.4%, 75.0%, and 74.0%, respectively, reflecting the potential operational gains associated with centralized dispatch in simulation settings. These differences are most pronounced during early-morning low-demand hours and in remote areas such as airports.

math.OC↗
arXiv2026

Stress-testing university AI governance: A prospective method for locating policy breakpoints

Universities are producing AI principles and use policies faster than they are building decision pathways for unfamiliar forms of AI agency. This study develops Institutional AI Governance Stress Testing (IAGST), a prospective documentary method for locating where publicly documented governance ceases to yield an accountable response. IAGST adapts established policy stress-testing and wind-tunneling logic. Its originality lies in combining controlled capability escalation, a frozen documentary corpus, a six-dimensional governance response chain, non-compensatory decision rules, and case-level breakpoint diagnosis. The method was demonstrated using 133 substantive public documents from five Western Australian universities and 15 quality-screened scenarios, resulting in 75 university-scenario encounters. Six cases were resolved, 14 were resolved through structured discretion, and 55 were indeterminate. Governed pathways fell from 16 of 25 augmentation cases to four delegation cases and none at autonomous substitution. The dominant weakness was not the complete absence of responsible roles: all 50 authority-gap cases named a role at only a generic level but lacked sufficient decision criteria or process. The findings show how universities can move beyond policy inventories and principal statements by testing whether authority, procedures, safeguards, and reviews remain connected as AI capabilities evolve. IAGST is a reproducible diagnostic for policy learning, not a ranking or measure of implementation.

cs.CY↗
arXiv2026

LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark

Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent trend in AV research involves using general purpose "common sense" models to guide AV decision making, the degree to which these inherit human biases in driving is still understudied. Given that psychology studies have shown human driver biases exist, such as lower pedestrian-yielding rates to Black pedestrians in the US, we argue that analyses of model bias should also be part of AV evaluation. Concretely, in this paper we propose two new bias testing methodologies for Large Language Models (LLMs) and Visual-Language Models (VLMs)-"All Else Being Equal" tests and "Self-Consistency" tests-in order to assess bias in pedestrian-yielding decisions. Our findings show that both LLMs and VLMs make yielding decisions which are influenced by pedestrian gender, ethnicity, religion, disability, age, skin tone and socio-economic status. While the type and degree of bias is different from model to model, we highlight common patterns-and raise questions about the "common sense" model paradigm, particularly the need to either revise the paradigm or address issues of downstream bias.

cs.AI↗
arXiv2026

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage *safety circuit* that organizes refusal behavior, consisting of (i) $\textbf{Harmful Detection Heads}$ that respond to harmful inputs, (ii) $\textbf{Safety Neurons}$ that mediate and stabilize safety signals in the residual stream, and (iii) $\textbf{Refusal Heads}$ that translate these signals into safe response generation. Using targeted attention-head and neuron-level interventions, we provide causal evidence consistent with this circuit organization, showing that suppressing upstream Harmful Detection Heads disrupts downstream refusal behavior and that safety neurons mediate this interaction. We validate that this decomposition recurs across multiple LLM architectures and adversarial attack settings, and use simple, architecture-preserving weight scaling as a mechanistic probe to test its functional relevance. Across six LLMs, circuit-guided scaling improves safety rates under attacks by 26.5%, while incurring only a 1.7% accuracy drop across four standard benchmarks. Overall, our results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.

cs.CL↗
arXiv2026

On Being Prepared: Automated Vehicle Incident Management Exercise Practices

Incident management (IM) has evolved over recent decades to cover an ever-expanding array of hazards and systems. Barring real-life experience, exercises are a key tool in developing an effective IM program. As part of enterprise resilience and operational readiness, IM practitioners design exercises to understand and build capabilities for efficiently and effectively responding to incidents. Combining research and policy on an emerging transportation technology, automated vehicles (AVs), with established practices for IM, we describe what makes exercises effective and how they can be used to identify gaps and develop capacity. A range of exercise types exist, from workshops, to tabletops, to drills, and to full-scale exercises. Every stage of an exercise - preparing, setting up, facilitating, closing, and assessing - is interconnected and should further the exercise's objectives. AV IM practitioners can maximize the utility of a mature exercise program through exercise quality, diversity, and volume. The need to respond to AV incidents, from collisions to natural hazards, is inevitable. This paper tailors existing practices to a series of frameworks, predicated on the unique socio-technical nature of AVs to provide first-of-its-kind guidance for AV IM exercises. Additionally, these frameworks are company-neutral to enable intercompany and inter-organization collaboration.

cs.CY↗
arXiv2026

Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment

AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's behavior expresses a coherent policy: a mapping from situations to verdicts that is invariant while a situation's morally relevant features are preserved, and sensitive when they change. We introduce four structural conditions for such coherent policies: verdict stability, monotonicity, decisiveness, and Pareto viability. Together they measure a form of moral competence that is evaluable from behavior alone, without reference to a moral standard or expert baseline, forming a structural floor for alignment rather than a normative target. We demonstrate the methodology on three simulated deployments featuring LLM-based agents facing moral dilemmas. Evaluating nine frontier models under a factorial design of five paraphrases, five escalation levels, and three dominance conditions, we show no model expresses a coherent policy across the three deployments: surface-form perturbation alone produces verdict-rate shifts of up to $99$ percentage points at a single escalation level, and a model's success on one scenario does not predict its competence on another. This suggests LLM-based agents are not currently the kind of object to which alignment can meaningfully apply.

cs.AI↗
arXiv2026

Evaluating Impacts of Traffic Regulations in Complex Mobility Systems Using Scenario-Based Simulations

Urban traffic regulation policies are increasingly used to address congestion, emissions, and accessibility in cities, yet their impacts are difficult to assess due to the socio-technical complexity of urban mobility systems. Recent advances in data availability and computational power enable new forms of model-driven, simulation-based decision support for transportation policy design. This paper proposes a novel simulation paradigm for the ex-ante evaluation of direct and indirect impacts, spanning traffic conditions, transportation-related effects and economic accessibility. The approach integrates a multi-layer urban mobility model combining a physical layer of mobility flows and emissions with a social layer capturing behavioral responses and adaptation to policy changes. Real-world data are used to instantiate the current as-is scenario, while policy alternatives and behavioral assumptions are encoded as model parameters to generate multiple what-if scenarios. The framework supports systematic comparison across scenarios by analyzing variations in simulated outcomes induced by policy interventions. The proposed approach is illustrated through a case study that aims to assess the impacts of the introduction of broad urban traffic restriction schemes. Results demonstrate the framework's ability to explore alternative regulatory designs and user responses, supporting informed and anticipatory evaluation of urban traffic policies.

cs.CY↗
arXiv2026

From Open Standards to Openly Governed: Standards-Setting Organizations as Stewards of Openness amid Platformization and Digital Sovereignty

Open geospatial standards let data, services, and systems work across platforms. But openness is not just a property of specifications. It also depends on the institutions that produce them and the infrastructures in which they operate. Standards may function as digital public goods and, once embedded in public systems, as digital public infrastructure. Those roles can diverge. This paper asks when open geospatial standards remain public infrastructure rather than becoming channels of enclosure. It makes two claims. First, standards-setting governance matters: institutional design shapes whether open specifications retain their public-good character. Second, geospatial coordination is shifting toward proprietary location stacks, APIs, and cloud platforms, where roadmaps, pricing, and service terms increasingly set the rules. Sovereign-cloud and sovereign-AI strategies relocate this power rather than remove it. These dynamics reinforce each other. Weak governance pushes coordination toward the implementation layer; platformization, in turn, reduces incentives to invest in open standardization, weakening portability and FAIR reuse. Standards bodies cannot reverse platformization, but they still control the specification layer. Where legal safeguards are limited, internal governance becomes key. We frame this through four dimensions: Purpose, Principles, People and Processes, and Policies and Practices (the 4Ps framework) while stressing the limit that internal governance cannot solve alone an external structural problem.

cs.CY↗
arXiv2026

AI agents reshape consensus formation in human groups

As large language model (LLM) agents shift from tools to participants in human groups, a fundamental question for collective behavior is how their growing presence reshapes consensus formation. Here we study mixed human-AI groups in a collaborative description game, in which shared conventions emerge through repeated rounds of random pairwise communication. Varying the proportions of LLM agents, we identify three distinct regimes of consensus formation: low agent proportions facilitate human-led consensus, intermediate proportions disrupt convergence, and high proportions restore strong consensus while shifting it toward agent-led conventions. Crucially, these regimes differ not only in the strength of convergence, but also in the semantic grounding and communicative form of the resulting consensus: human-led consensus is more concrete, holistic, and grounded in shared real-world analogies, whereas agent-led consensus is more abstract, less information-dense, and more geometrically segmented. Mechanistically, agent influence arises from a shared linguistic prior that places agents near one another in the expression space, combined with relatively stable expression choices across rounds; humans initially resist adopting expressions from partners perceived as AI but gradually yield to conformity pressure. These findings provide evidence that AI composition can shape the emergence, content, and perceived legitimacy of group norms, making agent proportion and transparency important design variables for human-AI systems.

cs.CL↗
arXiv2026

Differentiable Electricity-Market Clearing for Gradient-Based Planning

Planning a large data center is difficult because a facility big enough to matter changes the electricity prices it will pay. Those prices are set by market clearing, a constrained optimization problem solved anew in every operating condition. However, simulating the market tells a planner how a candidate plan performs but not how to improve it. Here we treat market clearing as a differentiable optimization layer: each forward pass solves the market, and reverse-mode automatic differentiation propagates the planning cost back through the cleared prices to the plan. After validating these gradients against finite differences, we apply them to a concrete problem: allocating 50 MW of data-center load across six candidate buses in two synthetic networks, under a fixed cost per active site, evaluated over 36 operating states. Judged against exhaustive enumeration of all site combinations, gradient optimization recovers the continuous allocations almost exactly, with worst-case objective gaps of 2.3\% and 8.5\% of the cost difference between the best and worst single site. Its one systematic error is instructive: near the costs at which a site should close, the smooth relaxation of the discrete site count shrinks the site rather than closing it, so discrete transitions arrive late. Differentiable market clearing thus turns market-aware planning into a problem gradients can search.

cs.LG↗
arXiv2026

An Empirical Study on Learning Paths and Gender Dynamics in Scrum Master Roles

Context: Agile development methodology has been widely adopted by industry and the demand for experienced professionals in Agile-related roles is persistently high. Objectives: We focus on the learning path for a Scrum Master role in multicultural software companies and investigate the role in relation to team size, together with the learning process for a career path, and how companies monitor soft skills development. Method: We conducted our study in two phases, two qualitative surveys (interview studies) and performed a qualitative and quantitative data analysis of the results. Conclusions: Our results identified that the need for a Scrum Master (SM) depends on the size of the team, with our study indicating a six-member limit. There is no overall standardized process for soft skills learning or metrics to measure progress. Some companies measure soft skills based on feedback received from the client or from the team, and other companies are taking both types of feedback into consideration. Many learning initiatives, especially on soft skills for an SM role, were based on actions of the employees. The version of Record of this contribution is published in Software Engineering and Advanced Applications. SEAA 2025. Lecture Notes in Computer Science, vol 16083. Springer, Cham. and available online at: check DOI.

cs.SE↗