Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2608.27902v1 Announce Type: new Abstract: Landing pages are goal-oriented web interfaces that must communicate a target-specific value proposition while organizing information flow, visual hierarchy, and calls to action (CTA). Although large language models can generate plausible webpage code from natural-language prompts, direct generation often yields generic templates and unsupported persuasive claims. We study target-grounded, reference-guided landing-page generation, where a system must create an executable page for a new target by adapting reusable patterns from real pages without copying them. We introduce LandingBench, a reference-profile dataset that abstracts real landing pages into section sequences, layout patterns, tone descriptors, visual emphasis, and CTA structure. Building on LandingBench, we propose LandingAgent, a three-phase agentic framework that profiles the target, constructs a reference-guided wireframe, and refines the page through critique-guided polishi
arXiv:2608.27899v1 Announce Type: new Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent class of techniques embeds subtle but detectable signals in generated text by modifying token sampling probabilities. However, such methods are unsuitable for open-source models, where users have white-box access and can easily disable watermarking during inference. In this work, we introduce OpenStamp, a watermarking technique that encodes the watermarking logic directly into the model weights by modifying only the final projection, or unembedding, layer. Through experiments across two models, we show that OpenStamp achieves superior detection performance, with minimal degradation in model capabilities compared to prior methods. The implanted watermark is explicitly designed, and empirically confirmed, to be more robust to pa
arXiv:2608.27855v1 Announce Type: new Abstract: Text generated by large language models (LLMs) has been shown to be stylometrically distinct from human-written text \citep{andreDetectingAIAuthorship2023, shahDetectingUnmaskingAIGenerated2023, oparaStyloAIDistinguishingAIGenerated2024, soto2024fewshot, liLinguisticDifferencesAI2025, selviogluFeatureExtractionAnalysis2025}. But LLMs are increasingly used not only to generate text but also to edit human writing, and it is unclear whether the two leave the same trace. We show that AI generation leaves a consistent ``stylometric footprint'': a small subset of features, primarily entropy and lexical diversity, consistently separates AI-generated text from human writing across 8 LLMs and 5 domains, while the remaining features depend heavily on the domain and generator. AI editing, however, does not reproduce the same footprint. Relative to their human-written sources, AI-edited texts show only a small increase in lexical diversity and a decr
arXiv:2608.27844v1 Announce Type: new Abstract: Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosystem of real-world content platforms where users continuously revise their expressions in response to moderation feedback. This mismatch creates a significant performance gap between offline benchmark scores and online deployment effectiveness. To the best of our knowledge, we present EvoHarmBench, the first dynamic adversarial evaluation framework for content moderation systems. The framework employs an iterative optimization loop that evolves evasion strategies at the semantic-cluster level, while simultaneously optimizing for evasion success and human readability. We systematically evaluate LLM-based defense models which are widely used in real world moderation systems. The evaluation covers 229 semantic sub-clusters across five violation categories, derived from 5,002 real-world adversar
arXiv:2608.27843v1 Announce Type: new Abstract: Contemporary language models can converse fluently and influence human decisions, yet their exchanges do not enter a continuing, vulnerable life of their own. Linguistic-agency theory identifies this missing connection as linguistic agency and characterizes it through embodiment, linguistic participation, and precariousness: a body that acts and bears consequences, interaction that changes both agent and partner, and a future that can be sustained or lost. Two coordinated studies examine how this organization can appear in artificial systems. First, we translate these relations into inspectable criteria for Synthetic Linguistic Agency (SLA) and identify several existing SLA systems. Second, building on Homeostatically Regulated Reinforcement Learning, we develop a mortality-grounded linguistic-reinforcement-learning model and instantiate it in an Embodied Mortal Agent (EMA). The EMA learns how ways of speaking change a partner's willingne
arXiv:2608.27816v1 Announce Type: new Abstract: Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifies internal model parameters to incorporate new knowledge, has demonstrated effective knowledge modification capabilities in factual knowledge editing tasks and may provide a potential solution for personalization. However, scaling model editing to personalization is non-trivial. Editing large amounts of user data increases computational cost and causes interference among edits, motivating the need for effective sample selection. To address this issue, we propose, PersonaEdit, a hidden representation clustering strategy that selects representative editing samples through proportional stratified sampling. Experiments show that model editing is effective for personalization, and that our selection strategy preserves most of t
arXiv:2608.27813v1 Announce Type: new Abstract: Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are evaluated by calculating the proportion of syntactic tree edges correctly reconstructed over an annotated corpus (as measured by undirected unlabeled attachment score). Here, we disaggregate this measure, considering undirected attachment score by label (UASL), which assesses the reconstruction accuracy of each syntactic relation separately, establishing important differences among relations that overlap linguistic distinctions. Moreover, we identify two factors that predict most of UASL's variability across relations: (i) the mean and dispersion of the linear distance (on a log scale) between the related words, and (ii) the diversity (similarity-aware entropy) of the syntactic relation's head. These results, which hold across a range of model sizes and architectures, shed light on the degr
arXiv:2608.27785v1 Announce Type: new Abstract: We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible audio and video evidence and decide whether the pair matches. On VideoLLaMA 2-7B-AV, three alignment configurations remain nearchance on the scored exact-string Yes/No subset of AVHBench, even though their output priors shift substantially. Similarly, off-the-shelf InternVideo2 experienced a 32.3% accuracy decrease specifically under cross-modal conflict, accompanied by a 17.3% instruction-following failure. We call this failure mode prior dominance: late-layer commitment to an internally preferred answer pattern that is weakly grounded in the conflicting inputs. To explain this behavior, we conduct a mechanistic interpretability analysis and find that commitment remains concentrated at 25.5 $\pm$ 1 layers. We show that stronger temporal alignment changes answer bias, but do not improve compo
arXiv:2608.27760v1 Announce Type: new Abstract: We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual information across any span of $k$ contiguous symbols. We construct such languages with increasing $k$, finding that LLMs trained on them achieve comparable cross-entropy loss regardless of antilocality, but converge more slowly on more antilocal languages. Our findings support the idea that non-local dependencies are more difficult to learn, but the evidence for this bias comes from learning speed rather than learning success.
arXiv:2608.27756v1 Announce Type: new Abstract: Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olympiad puzzles provide a controlled setting where all answers derive solely from expert-designed context examples without external knowledge. Removing individual context examples can eliminate information needed for specific questions while leaving the rest of the puzzle unchanged. We leverage this to introduce a diagnostic framework for analyzing individual context examples. Using 53 UK Linguistics Olympiad puzzles, we generate two modified variants by deleting a single context example: (1) uniform random deletion, and (2) targeted deletion (inspired by error-correcting codes) to remove a structurally load-bearing example uniquely carrying necessary information. We formalize this impact using a Question Damage Score to classify puzzles as fragile or robust. Evaluating three frontier LLMs un
arXiv:2608.27729v1 Announce Type: new Abstract: Function routing -- selecting the correct API call from a fixed catalog given a natural-language request -- is a deployment problem where small students are attractive but knowledge distillation gains are typically reported single-seed, at scales where seed variance is unknown. On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, we compare eight KD variants against supervised cross-entropy, using three to six seeds for key configurations. We find: (i) per-seed standard deviation ranges from 2.8 to 48.7 percentage points, swallowing every claimed KD gain below five points; (ii) three of seven KD variants exhibit bimodal collapse, with at least one in three to five seeds falling below 55% accuracy while the others train normally, and a fourth showing elevated variance; (iii) collapse has distinct modes -- wrong-function selection for ce_kd and ce_paraphrase, and a previously undocumented output-truncati
arXiv:2608.27672v1 Announce Type: new Abstract: We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only successful game trajectories from Playpen, b) weighted turn-level SFT, and c) teacher-guided SFT. The teacher model (which is a larger model) is only used to fix formatting and evaluate examples, but does not create new gold actions. Our final model scores 57.12 clemscore and 42.68 statscore on the public Playpen validation. In the officially released challenge results, our model obtains the second-highest Playpen clemscore delta among submitted systems (which is approximately +36 over its base model). Our findings suggest that imitating full trajectories helps with playability, while turn-level and teacher-guided training usually improve decision-making and increase the overall score. Alternative procedurally heavy approaches like replay-repair and hard-example mining did not help, which sug
arXiv:2608.27661v1 Announce Type: new Abstract: In Retrieval-Augmented Generation (RAG), retrieval may provide insufficient or conflicting information needed to answer a question. The system should not only know when to answer but also be able to identify cases in which the documents provided in RAG are insufficient or contain conflicting information. This can be framed as a three-way classification problem, where we use the model's internal signals to determine whether the provided information in the input can be classified as sufficient, insufficient, or conflicting. We create a controlled benchmark dataset that replicates a RAG setup with fictitious information and labels each instance as answerable, insufficient, or conflicting. We use hidden activations and attention-derived features as inputs to train a lightweight linear model to distinguish among the three classes. Across 16 language models spanning different architectures and a range of model sizes, our feature-based router co
arXiv:2608.27658v1 Announce Type: new Abstract: Subword tokenization hinders low-resource language processing by imposing frequency patterns from dominant languages onto script-sharing variants. Byte-level models bypass this issue by processing raw UTF-8 characters, yet they create a granularity mismatch for word-level tasks in non-Latin scripts. Hierarchical byte-level architectures address this mismatch by grouping bytes into word-aligned chunks. However, these architectures require massive training data and suffer from representational misalignment when paired with frozen subword-based language models. In this paper, we propose an adapted hierarchical network framework that bridges this modality gap without extensive training. Our method initializes byte embeddings directly from the subword representations of a frozen base model. We apply a chunk alignment loss to project dynamically grouped byte chunks toward precomputed subword targets, and interleave lightweight part-of-speech (P
arXiv:2608.27514v1 Announce Type: new Abstract: Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token sequences in a fixed left-to-right order, dLLMs require speculating over denoising trajectories-sequences of multi-token updates with explicit positions and unmasking orders. We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration and verifies them through blockwise parallel evaluation with bidirectional attention masking. Our method further introduces inter-block speculation, exploiting diffusion models' bidirectional structure to perform cross-block lookahead. We formally characterize when this approach is exact and identify trajectory drift as the fundamental co
arXiv:2608.27510v1 Announce Type: new Abstract: Transcoder attribution graphs are usually trained to explain why a model assigns high probability to a particular next token. We introduce Concept-Targeted Attribution (CTA), which instead trains attribution graphs with respect to a linear probe direction. CTA therefore yields probe-specific circuits that explain why an internal concept representation arises in a prompt, independently of whether it is expressed in the generated token. Using Cross-Layer Transcoders, we show that these probe-targeted graphs contain predictive structure: graph-level features predict probe accuracy across four widely studied concept categories ($\rho = 0.91$, $R^2 = 0.84$), while local features identify the sparse components driving per-prompt classification. This connects probe performance to interpretable circuit structure, allowing us to ask not only whether a probe works, but which internal computations make it work. Causal ablations further show that pro
arXiv:2608.27505v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models (LLMs) with human preferences. However, traditional RLHF relies on scalar reward signals that lack interpretability and fail to capture the multifaceted nature of response quality. Rubric-guided reinforcement learning addresses these limitations by introducing structured, interpretable evaluation criteria, or rubrics, as the backbone of reward design, feedback generation, and policy optimization. In this survey, we introduce a Bayesian framework that defines constitutions as prior distributions $P(R)$ over evaluation criteria and rubrics as conditional instantiations $R_x \sim P(R|x)$. Under this unified view, we present a taxonomy of rubric-guided RL along the prior-posterior axis, covering constitutional AI, instance-specific rubrics, process-level supervision, self-evolving rubrics, and their agentic and multimodal exte
arXiv:2608.27501v1 Announce Type: new Abstract: Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question whether models truly internalize mathematical concepts or merely memorize solution patterns. In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding, but remains underdeveloped in current LLMs. Enhancing this capability through preference optimization presents two key challenges: (1) the model's limited example-based reasoning ability makes constructing effective preference pairs inherently difficult; and (2) capability acquisition is progressive, as the model must first learn to adopt this strategy before learning to apply it correctly. Therefore we propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI), whic
arXiv:2608.27481v1 Announce Type: new Abstract: Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually translate an entire example into one language. This hides failures at language boundaries inside the reasoning chain. We introduce XHotpotQA, a controlled benchmark for cross-lingual knowledge composition over mixed-language evidence. Each instance is modeled as an evidence-dependency graph whose question, bridge evidence, answer-bearing evidence, and distractors have explicit language assignments. The audited resource contains 15,661 training and 7,405 validation instances, with sentence-level support supervision and supplied distractors. In validation, 99.81% of items cross the question-to-gold-evidence language interface and 95.60% use gold paragraphs in different languages. Across three reader artifacts, full question-evidence mismatch is associated with 10.25 to 15.79 lower Unicode-awar
arXiv:2608.27470v1 Announce Type: new Abstract: Entity Disambiguation (ED) is a key task for constructing and using knowledge graphs. State-of-the-art neural approaches commonly model ED as a single task, although it consists of two distinct subproblems: retrieving candidate entities and selecting the correct one given context. Dual-encoder models optimize for both within a shared embedding space, forcing representations to balance high-recall retrieval with fine-grained selection, and they require trained retrievers, which are costly to maintain as knowledge graphs change. While recent work has begun to combine retrievers with LLM-based selectors, the interplay between the two stages has not been studied systematically. In this paper, we present a systematic comparison of retrieval strategies for candidate generation under a shared LLM-based selection stage, combining sparse retrieval (BM25), Web KB search, and a state-of-the-art trained dense retriever with several open- and closed-s
arXiv:2608.27466v1 Announce Type: new Abstract: Web content extraction is essential for reliable LLM data pipelines, yet existing methods often struggle to jointly satisfy accuracy, scalability, and adaptability. General-purpose extractors can be applied broadly, but they are often brittle on publisher-specific layouts and richer extraction targets such as metadata, images, and tables. Direct LLM-based extraction offers greater flexibility, but incurs substantial cost and latency at scale, while manually engineered publisher-specific parsers can achieve high accuracy but require substantial human effort to build and maintain. We introduce PACE, an agentic framework for learning publisher-specific extraction configurations from representative pages and user requirements. During training, PACE uses LLMs to analyze page structure and aggregate reusable extraction patterns. At inference time, the learned configurations instantiate a fixed deterministic extractor template, enabling scalable
arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging. While existing PLM- or LLM-based methods perform well, they typically apply a single reasoning process to all samples. This overlooks fine-grained linguistic nuances and causes unnecessary computation for simpler cases. We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent. Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework that first performs fine-grained classification and then adapts to specific categories. Specifically, for Shallow samples with surface-identifiable intents, the framework adopts lightweight prompt-tuning for rapid classification; fo
arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ability consists of multiple categories, such as analogical, structural, and cause-effect, each capturing a different aspect of higher-order understanding. To examine the performance of multimodal large language models (MLLM) on these relational inference tasks, we developed SciReC, a model-adaptive multimodal academic dialog benchmark. As the relational reasoning process involves multiple representations and various factors (visual understanding, exhibiting knowledge, and memory recall), we propose DMRA, a deficit-based diagnostic framework that quantifies the contribution of these components to identify the primary cause of unsuccessful cases. Claude 4.6 achieved the best performance on the overall relational score with 73\%, followed by GPT 5.4 with 68\%. Performance trends indicate that
arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large multilingual vocabularies. We reformulate the output projection followed by top-k token selection as a maximum inner product search over token embeddings and replace the dense vocabulary projection with an HNSW-based vector index. The resulting output head retrieves only a small candidate set of high-scoring tokens and can be integrated into existing decoding pipelines by scattering retrieved logits into a sparse full-vocabulary tensor. On CPU inference with Gemma 3, Llama 3.2, and Qwen 3 models, our method substantially accelerates the output projection and improves end-to-end batch-size-one decoding throughput by up to 82% for Gemma 3 270M, while preserving generation quality under AlpacaEval evaluation. These results suggest approximate retrieval is a practical alternative to dense outp
arXiv:2608.26152v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit unprecedented natural language generation and many text-based problem-solving capabilities. Indeed, in many language-based tasks, for example routine coding, these artificial intelligence models have reduced, or even eliminated, the need for human input. But rather than replacing human cognitive effort, LLMs may instead serve as cognitive tools to extend human abilities, particularly when they are engaged in a task requiring open-ended conceptual exploration and creative ideation. However, we are yet to understand how these models may enhance such generative human cognitive abilities in human--AI interactions. In this study, we explore and evaluate the ability of LLMs to follow and enhance human mental trajectories during semantic memory search. To test this, we use the semantic fluency task (SFT), a classic cognitive paradigm requiring generative semantic memory retrieval that has long serve
arXiv:2602.02745v2 Announce Type: replace Abstract: The ethics of human-robot interaction (HRI) have been discussed extensively based on three traditional frameworks: deontology, consequentialism, and virtue ethics. We conducted a mixed within/between experiment to investigate Sparrow's proposed ethical asymmetry hypothesis in human treatment of robots. The moral permissibility of action (MPA) was manipulated as a subject grouping variable, and virtue type (prudence, justice, courage, and temperance) was controlled as a within-subjects factor. We tested moral stimuli using an online questionnaire with Perceived Moral Permissibility of Action (PMPA) and Perceived Virtue Scores (PVS) as response measures. The PVS measure was based on an adaptation of the established Questionnaire on Cardinal Virtues (QCV), while the PMPA was based on Malle et al. [39] work. We found that the MPA significantly influenced the PMPA and perceived virtue scores. The best-fitting model to describe the relation
arXiv:2601.07576v2 Announce Type: replace Abstract: Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance across multiple modalities remain scarce. To address this gap, we present SOPHIAS (Student Oral Presentation monitoring for Holistic Insights & Analytics using Sensors), a 12-hour multimodal dataset containing recordings of 50 oral presentations delivered by 65 undergraduate and master's students at the Universidad Autonoma de Madrid, comprising 46 individual presentations with a mean presentation duration of 9 min 48 s (SD = 33 s) followed by a mean Q&A duration of 6 min 28 s (SD = 3 min 02 s), and 4 group presentations with a mean presentation duration of 14 min 11 s (SD = 1 min 40 s) followed by a mean Q&A duration of 8 min 22 s (SD = 1 min 21 s). SOPHIAS integrates eight timestamped sensor streams from high-definition webcams, ambient and webcam audio, eye-tracking glasses, smartwatch physiolog
arXiv:2508.05281v3 Announce Type: replace Abstract: Algorithmic fairness research comes almost entirely out of North America and Western Europe, so we know little about how people elsewhere judge the algorithms they already rely on every day. We asked people in Bangladesh directly: a bilingual (Bangla and English) survey of 199 participants rated fairness across three everyday scenarios -- ride-sharing prices that shift with context, AI beauty filters that reshape appearance, and large language models that handle cultural values differently than a human would. Four patterns stood out. Context changes the verdict even when the outcome doesn't: a 20% price surge during a medical emergency feels less fair than the identical surge on a casual trip (2.00 vs. 2.17 on a 5-point scale, Wilcoxon p = .006), a small effect uneven across income groups (largest among middle-income participants). People already view surge pricing critically in general; context sharpens the judgment rather than creat
arXiv:2608.28165v1 Announce Type: cross Abstract: AI agents are evolving into long-running computational entities that can invoke tools, maintain memory, and complete complex tasks across applications. In real-world settings, completing a task often requires humans and AI to take turns leading its execution. Such alternation depends on the seamless handoff of the work state of the task between humans and AI. Existing agent systems, however, provide humans and AI with separate work environments. AI agents must therefore rely on additional bridges to continue work: either developers build task-specific interfaces to access the work state, or users manually transfer relevant parts of it through screenshots or textual descriptions. Both approaches make handoffs costly and scale poorly. We propose Human-AI Co-inhabitation, a type of work environment that enables humans and AI to seamlessly take turns continuing work on the same task, and design and implement CrabOS to realize this concept.
arXiv:2608.28160v1 Announce Type: cross Abstract: FPGA-GPP heterogeneous systems combine software flexibility with the performance and energy efficiency of reconfigurable hardware. However, determining which application tasks should execute on the GPP or FPGA requires extensive expertise and design-space exploration, particularly when user objectives vary across latency, communication, resource utilisation, and power. This paper proposes Gen-TAS, a knowledge-grounded LLM framework for user-specific FPGA-GPP task allocation. By combining task-graph analysis with RAG, Gen-TAS grounds LLM reasoning in historical implementation knowledge and generates multiple explainable strategies tailored to the specified objectives. Human-in-the-loop selection and a deterministic backend connect LLM-generated decisions to reproducible FPGA SoC implementations. Experiments on CNN and SDR workloads across multiple LLMs demonstrate stable, requirement-driven allocation. Under latency-oriented objectives,
arXiv:2608.27638v1 Announce Type: cross Abstract: Course-based undergraduate research experiences (CUREs) broaden access to authentic scientific inquiry through responsive instructor support as research problems become increasingly complex. Generative artificial intelligence (GenAI) may extend this support by providing individualized assistance that can adapt as student needs change. However, how embedding GenAI within a CURE to provide support across the research process impacts student inquiry, collaboration, and scientific reasoning remains unresolved. Here we use longitudinal qualitative data collected across three semesters of a bioinformatics and genomics CURE to show that GenAI expanded the intellectual reach of the research experience in three distinct ways. First, personalized, on-demand scaffolding allowed students to move beyond the boundaries of instructor expertise and transform their own interests into researchable inquiry, with all teams developing distinct self-directed
arXiv:2608.27467v1 Announce Type: cross Abstract: We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participated in Subtasks 2 (evidence identification), 3 (answer generation), and 4 (answer-evidence alignment). For Subtasks 2 and 3, we propose an answer-first pipeline in which the model generates candidate answers citing specific note sentences before classifying the full evidence set, exploiting the asymmetry between judging relevance in the abstract versus relative to a generated answer. For Subtask 4, we apply self-consistency voting over five independent model calls, retaining links by vote threshold. Our pipeline ranked third on evidence identification (Strict Micro F1 62.90), ninth on answer generation (Overall 31.90), and fifth on answer-evidence alignment (F1 79.81). A post-hoc linguistic analysis of 45 stylistic features reveals that model outputs remain 3.2 Flesch-Kincaid grade levels
arXiv:2608.27464v1 Announce Type: cross Abstract: This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate whether to engage with explanations based on three types of expected utility: instrumental (will it help me act better?), hedonic (will it make me feel better?), and cognitive (will it improve my understanding?). Each utility is estimated through a lens shaped by well-documented cognitive biases, including illusion of control, automation bias, unrealistic optimism, impact bias, overconfidence, and confirmation bias. These biases can lead to two failure modes: excessive information-seeking that fragments attention without improving decisions, and insufficient information-seeking that leaves critical risks and misunderstandings unexamined. This challenge is particularly acute for agentic AI sys
arXiv:2608.28420v1 Announce Type: new Abstract: The integration of AI into qualitative design research presents a fundamental tension: how do we leverage AI while preserving the subjective, intuitive judgments that define design expertise? This paper examines this question through a case study of analyzing 20 user responses about video conferencing platforms for educational contexts. We argue that AI sensemaking tools risk flattening the rich data patterns, amplifying contradictory textures of user feedback into sterile categories thereby transforming design research from an interpretive craft into a mechanical sorting exercise (rigid and formal). Through comparative analysis of AI-assisted sensemaking versus human-centered approaches to the same dataset, we identify when algorithmic efficiency enhances understanding and when it diminishes the designer's interpretive agency (uncovering hidden needs, critical enquiry, what if enquiries, making decisions, having trade-offs). We present a
arXiv:2608.28373v1 Announce Type: new Abstract: Integrating Artificial Intelligence (AI), particularly generative AI, into medical training has prompted concerns about learner over-reliance, misuse, and erosion of foundational clinical competencies. We propose a conceptual reframing at the decision level: the problem is not misuse but misclassification - a mechanistic failure of real-time metacognitive evaluation in selecting a subzone-inappropriate AI interaction mode. Drawing on "SCAN" (Substitute, Complement, Aid, Non-Negotiable), a human-centric decision-making framework for generative AI task allocation grounded in Vygotsky's Zone of Proximal Development and metacognition, we advance the emerging social-constructivist conversation around AI in medical education by offering a testable account of AI's role in clinical reasoning development. This framework yields testable predictions for how misclassification can be detected, mitigated, and, more importantly, prevented in the clinica
arXiv:2608.28064v1 Announce Type: new Abstract: Anchoring - the choice of frame of reference for mixed reality (MR) interface elements - is a critical design decision involving trade-offs between accessibility, interaction comfort, and visual interference. Despite its importance, user preferences for anchoring across different mobility contexts and interface properties remain poorly understood, as prior work has largely focused on specific tasks or fixed interface configurations. We address this through a mixed-methods user study in which participants configure anchoring strategies across different mobility conditions and interface types. Combining behavioral analysis with structured qualitative inquiry, we analyze how participants select and reason about anchoring modes. Our results show a clear transition from world-anchored interfaces in stationary contexts to body-anchored interfaces during locomotion. However, no single body anchor consistently dominates, highlighting the personal
arXiv:2608.28050v1 Announce Type: new Abstract: Learning to Defer (LtD) extends supervised learning by allowing a Machine Learning (ML) model to defer harder or less confident decisions to a human expert. Despite being geared for human-AI collaboration, LtD strategies neglect the potential negative interference of human cognitive biases. Our contribution is twofold. First, we demonstrate that standard LtD strategies show class-dependent sampling bias in classification tasks in practice, and thus may disproportionately defer the minority classes when applied to imbalanced datasets. Second, we show that such asymmetries in task delegation may trigger human biases, ultimately leading to poorer downstream decision making. Specifically, we conduct a user study ($N=226$) where participants complete a classification task on a set of deferred items, with conditions presenting different levels of class imbalance. Our results show that participants exposed to a highly imbalanced rejection set ac
arXiv:2608.28001v1 Announce Type: new Abstract: Creative professionals rarely design for themselves--they design for audiences whose preferences they must anticipate. Yet current text-to-image exploration tools derive diversity entirely from the designer's own input--their prompts, their chosen dimensions, their search queries--confining exploration to what the designer already knows to look for. We present FocusGen, an interactive system that introduces external perspectives into visual design exploration through a "virtual focus group" of simulated persona agents. In contrast to prior persona systems in which multiple agents converge as critics on a single evolving artifact, FocusGen uses personas as parallel generators: each agent--constructed from demographic data, a procedurally generated backstory, and aesthetic preferences elicited through interviews--independently drives an iterative generation loop that produces its own visual concept, transforming one design brief into a spec
arXiv:2608.27932v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly equipped with augmented reasoning capabilities to generate rationales that support human decision-making. Yet these text-dense rationales often impose substantial cognitive burdens. Building on a formative co-design study that identified user preferences for non-linear reasoning representations, we developed Graphionale as a testbed for empirically studying argument-map-style rationale visualization. This system transforms linear LLM rationales into interactive, multi-level graphs. It explicitly structures logical relationships (e.g., conclusions, premises, support, and objections), while further extracting entities and relations within each statement to construct condensed node-link representations. We conduct a large-scale online user study (N = 204) to examine when graphical rationales are more effective than textual ones, across varying task modality (verbal vs. visual reasoning), rational
arXiv:2608.27842v1 Announce Type: new Abstract: A common expectation in visualization research is that outcomes recommend how researchers and practitioners take action or make design decisions. We often express these as "guidelines." Yet, the term "guideline" is both ambiguous and loosely defined, and what one researcher considers a guideline may be too broad, too loose, or too strict for another. We take a closer look at a broader set of terms that can express desirable results around visualization research, and untangle how these words are understood in the community in relation to other similar terms. We base our work on an exploratory study with experts, followed by a crowdsourcing study with a separate mapping phase (n=30) and rating phase (n=42) targeting input from the broader visualization community, and an analysis of the use of terminology in 3,877 IEEE VIS papers published from 1990 to 2024. Based on our findings, we call for more nuanced, precise discussions of research out
arXiv:2608.27799v1 Announce Type: new Abstract: AI tools that support collaborative discussion typically treat the discussion as a standalone task, focusing only on its content and setting aside the social context of the group having it. But it is groups with a shared history, with their own norms, hierarchies, and relationships, where the most tangled and complex discussions tend to arise. These discussions cannot be understood apart from that context, and AI that overlooks it risks failing to convey what a discussion means, or even misrepresenting it. Drawing on two studies of how experienced Wikipedia editors read and make sense of discussions, we propose an AI-Assisted Sensemaking Model for Collaborative Discussions, which captures not only a discussion's arguments but also the norms and participants behind it, along with the context that gives each meaning. In this model, the system supports the early stages of the sensemaking process, and the degree to which it performs interpret
arXiv:2608.27684v1 Announce Type: new Abstract: Background: Deceptive patterns are interface design strategies aimed at misleading users or favoring specific interests, compromising user experiences and ethical privacy principles. These patterns involve exploit different issues of the interaction between humans and technology, revealing gaps in the scientific literature regarding their understanding and working mechanisms. Purpose: This research characterizes deceptive patterns as a sociotechnical phenomenon, integrating human and technical dimensions while offering a self-explainable interactive catalog to raise awareness among users and designers. Methods: To characterize deceptive patterns as a sociotechnical phenomenon, a systematic literature review in Computer Science was conducted, and the Semiotic Framework was applied to analyze and organize the sociotechnical aspects of identified patterns in an integrated manner. An exploratory evaluation of the interactive catalog was condu
arXiv:2606.09835v2 Announce Type: replace-cross Abstract: Visualization researchers utilize workshops both for applied research and to engage different populations with visualization-based activities. While there are many benefits to running visualization workshops, their utility and impact rely on the presence of a researcher who has deep knowledge about visualization theory and practice. In this work, we introduce workshop-in-a-box as a design concept intended to challenge the researcher-centric approach to data physicalization workshops. Through a design study with a socially innovative organization, we deployed several data physicalization workshops that our collaborator ran instead of us. Based on this experience, along with two accompanying case studies that validate the concept, we present material and procedural considerations for how to put data physicalization workshops into a box and the implications it has for extending visualization research outside the bounds of academia.
arXiv:2605.02016v4 Announce Type: replace-cross Abstract: Therapy and life-coaching apps have grown rapidly in number, variety, and popularity. At the same time, their users often share highly sensitive and personal information, including mental health issues, trauma experiences, fantasies, desires, and relationship difficulties. This prompts the need to examine privacy practices across the ecosystem. In this paper, we present a comprehensive analysis of a corpus of 25 popular Android mental health and life-coaching apps, such as Replika and Headspace. It builds on static analysis and dynamic network traffic analysis, coupled with identifying gaps between each app's observed behavior and its privacy policies. Our analysis highlights serious concerns and substantial transparency gaps. First, every app in our corpus embeds at least one tracker SDK not named in its privacy policy, and 85\% of the apps we instrument fail to disclose at least half of the trackers detected in their APKs. Sec
arXiv:2604.21751v2 Announce Type: replace-cross Abstract: 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 highlighti
arXiv:2507.20409v3 Announce Type: replace-cross Abstract: 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 f
arXiv:2505.13673v2 Announce Type: replace Abstract: AI governance has transitioned from soft law, such as national AI strategies and voluntary guidelines, to binding regulation at an unprecedented pace. This evolution has produced a complex legislative landscape: blurred definitions of "AI regulation" mislead the public and create a false sense of safety; divergent regulatory frameworks risk fragmenting international cooperation; and uneven access to key information heightens the danger of regulatory capture. Clarifying the scope and substance of AI regulation is vital to uphold democratic rights and align international AI efforts. We present a taxonomy to map the global landscape of AI regulation. Our framework targets essential metrics-technology or application-focused rules, horizontal or sectoral regulatory coverage, ex ante or ex post interventions, maturity of the digital legal landscape, enforcement mechanisms, and level of stakeholder participation-to classify the breadth and d
arXiv:2309.12355v2 Announce Type: replace Abstract: Innovation in Information and Communication Technology (ICT) has become one of the key economic drivers of our technology-dependent world. Digital devices/systems have become so pervasive that it is hard to imagine new technology developments that are not totally or partially influenced by ICT innovations. Furthermore, the pace of innovation in ICT sector over the last few decades has been unprecedented in human history. In this paper, we argue that the ICT innovation paradigm has crucially shaped collective expectations and imagination about what technology more broadly can actually deliver, particularly for a more sustainable and equitable world. These expectations have often crystalised into a widespread acceptance, among general public and policy makers, of techno-solutionism. We emphasise the role of electronic microchips in deriving relentless innovation and its impacts. We identify the many impacts of this innovation cycle into
arXiv:2608.28405v1 Announce Type: cross Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking practical help over multiple turns in culturally grounded scenarios. We introduce CultureConverse, a scalable, multilingual simulation and evaluation harness for culturally grounded assistant dialogue that covers 10 East and Southeast Asian regions, 58 subgroup identities, and 7 domains. Each simulated and evaluated episode produces a scored interaction where the assistant assists the user and infers cultural constraints from partial information. The resulting CultureConverse-DS dataset contains 14,610 benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues. In our benchmark evaluation of 18 models, GPT-5 mini achieves the highest assistance quality. Human annotation experiments suggest that our evaluation framework is a sufficient proxy for
arXiv:2608.28228v1 Announce Type: cross Abstract: Generative AI systems are increasingly used to answer personal questions and mediate everyday practices, including religion. However, existing discussions around AI alignment and ethics have largely centered secular, Western, and Abrahamic assumptions about religion, offering limited attention to other faith-based traditions. In this paper, we examine how Hindu users engage with generative AI systems in relation to their religious knowledge, belief, and practice. Drawing on 15 semi-structured interviews with Bangladeshi Hindu participants, we analyze how users interpret AI-generated religious representations, scriptural explanations, devotional interactions, and synthetic religious media. We found that AI can be both accessible and ethically troubling. While AI supported scriptural inquiry, devotional visualization, and religious storytelling, our study also identified concerns about theological flattening, cultural misrepresentation, d