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:2606.31186v1 Announce Type: new Abstract: Spontaneous speech is a vital non-invasive biomarker for Alzheimer's Disease (AD), yet many systems overlook non-linear structural disruptions and clinical heterogeneity in pathological language. We propose a Multi-View Gated Graph Attention Network that transcribes audio via Automatic Speech Recognition (ASR) to construct semantic, dependency, and co-occurrence graphs, characterizing speech through a "content-structure-flow" framework. Notably, the co-occurrence graph leverages Pointwise Mutual Information (PMI) from a normative corpus to quantify narrative logic and linguistic deviation. To address symptomatic diversity, an adaptive gated fusion mechanism dynamically integrates these views. Evaluated on the ADReSSo dataset, our model achieves 90.00% accuracy. Ablation results confirm that the PMI-based graph and heterogeneity-aware gating are essential for robust classification across diverse clinical populations. Our source code is pub
arXiv:2606.31166v1 Announce Type: new Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual reasoning and graph message passing within a masked diffusion language model, a language model with bidirectional attention and generative decoding. For each graph instance, method linearises a sampled local neighbourhood into a token sequence and injects graph structure through a topology attention mask, which realises message passing over the graph. Because the diffusion language model can both interpret and generate text, the method adapts to different tasks simply by changing the prompt, suppo
arXiv:2606.31145v1 Announce Type: new Abstract: Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be retained throughout decoding, making full GPU caching prohibitively expensive without compression. Existing KV cache compression methods struggle to balance efficiency with faithful context preservation. Token eviction discards information, while semantic grouping fixes compression decisions at prefill time; neither can recover token-level detail from a compressed span once it becomes relevant during generation. As a solution, we propose SeKV, a resolution-adaptive semantic KV cache that organizes context into entropy-guided semantic spans and stores them across a GPU-CPU memory hierarchy without discarding information. Each span keeps a lightweight summary vector on GPU for coarse routing and a low-rank SVD basis on CPU for on-demand token-level reconstruction. A
arXiv:2606.31087v1 Announce Type: new Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose \emph{Training-Free Gated Reranking}, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU datasets and 9 MT domain-language combinations, demonstrate that our approach reduces computational costs by 15\%-80\% while improving average performance by up to 2\%. These findings indicate that higher computational cost does not guarantee better performance, and that reranking is most beneficial when targeted at high-uncertainty instances.
arXiv:2606.31074v1 Announce Type: new Abstract: Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the adversarial RAID. This framework marks a pioneering effort in statistical methods to enhance detection reliability against attacks. We release our data and code at https://github.com/baoguangsheng/triospect.
arXiv:2606.31058v1 Announce Type: new Abstract: The composition of author teams is an important factor influencing the novelty of academic papers. However, existing studies have paid limited attention to the role of institutional composition, and most novelty measures remain at a general level, making it difficult to explain the specific sources and types of novelty in papers. Taking the field of natural language processing as an example, this study investigates the relationship between team institutional composition and the fine-grained novelty of academic papers. Author teams are classified into three types: academic institutions, industrial institutions, and mixed academic and industrial institutions. Four types of fine-grained knowledge entities are extracted from full-text papers, including methods, datasets, tools, and metrics. The novelty of papers is then measured based on entity combinations, and pairwise combinations of different entity types are further analyzed to examine t
arXiv:2606.31055v1 Announce Type: new Abstract: Speech-to-speech (S2S) AI agents are advancing rapidly, yet evaluation lacks interpretable speech-native measures for conversational prosody and rhythm. Because $F_0$, speaking rate, articulation rate, and pausing shift with model-predicted speaker traits and interaction state, pooled human statistics can be poorly calibrated for evaluating a particular output. Using 4000+ hours of dyadic English conversation from the Seamless Interaction dataset, we construct matched reference regimes for $F_0$ mean, $F_0$ expressivity, speech rate, articulation rate, pause ratio, and mean pause duration. We then define a percentile-based evaluation protocol: extract the same metrics from an S2S output waveform, compare them to the closest matched human reference stratum, and report percentile deviations or 5th-95th percentile out-of-regime flags. On held-out human rows, pooled references over-flag state-conditioned $F_0$ expressivity and rhythm, while m
arXiv:2606.31041v1 Announce Type: new Abstract: Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, heterogeneous SQL dialects, and complex analytical workloads requiring nested aggregations, temporal reasoning, and multi-table joins. We present a semantic-layer-mediated NL2SQL agent that decouples semantic intent from physical SQL execution. Rather than generating SQL directly over raw schemas, the agent reasons over a curated semantic layer through a compact intermediate representation called the Semantic Model Query (SMQ). A deterministic compiler translates each SMQ into dialect-specific SQL, providing verified building blocks that the agent composes into the final query. The system employs a constrained think-act loop, supports SQLite, BigQuery, and Snowflake backends, and is integrated into an end-to-end eval
arXiv:2606.31039v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulative linguistic patterns such as logical fallacies remains underexplored. Prior work has primarily examined whether LLMs can identify or classify fallacies, leaving their robustness against fallacious persuasion insufficiently studied. To address this gap, we introduce LoFa (Logical Fallacy), a comprehensive benchmark for evaluating LLM robustness against fallacies. LoFa is constructed through a multi-agent pipeline that pairs factual questions with fallacious arguments, and is accompanied by a multi-round debate framework for assessing model resilience under sustained adversarial persuasion. To disentangle fallacy robustness from a model's inherent knowledge limitations, we further propose Logical Fallacy Resistance at k (LFR@k), a metric that quantifies resistance to fallacious attacks. Experiments show that LLMs exhibit varying levels of
arXiv:2606.31033v1 Announce Type: new Abstract: In this paper, we propose CORTEX, a token-level hallucination detection method for Retrieval-Augmented Generation (RAG). In long-form RAG outputs, hallucinations often arise in localized spans rather than throughout an entire response. CORTEX therefore identifies ungrounded content at the token level, enabling fine-grained localization of hallucinations. The key intuition behind CORTEX is that tokens grounded in retrieved documents should be more strongly influenced by those documents than hallucinated tokens. To capture this document-induced effect, CORTEX compares internal representations of a large language model (LLM) under two conditions: with and without the retrieved documents. Instead of relying solely on each token's immediate sensitivity to the retrieved documents, CORTEX also leverages the propagation of document-grounded information through preceding tokens, reducing false positives for tokens whose evidence has already been a
arXiv:2606.30989v1 Announce Type: new Abstract: Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks.
arXiv:2606.30987v1 Announce Type: new Abstract: Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Forecasting tournaments offer a natural testing ground: probabilistic judgments are paired with natural-language rationales and scored against realized outcomes. We introduce Explanation Quality Markers (EQMs), a set of sixty theory-guided reasoning patterns scored by large language models (LLMs). In a pre-registered analysis of over 55,000 forecast-rationale pairs from a multiyear forecasting tournament, EQMs predict accuracy at both the forecast and forecaster levels, consistently outperforming pre-LLM text-analysis methods. More than 90% of statistically significant pattern-level EQM-accuracy correlations match our directional hypotheses. The signal is asymmetric: EQMs identify likely underperformers more reliably than they distinguish the very best forecasters. Benchmarked against traditiona
arXiv:2606.30973v1 Announce Type: new Abstract: Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as an epistemic signal essential to common-ground construction, rather than noise to be minimized. However, FPO and its implementations assume shared perceptual contexts, where friction arises from differently interpreted propositions over the same scene, which we define as propositional asymmetry. We extend FPO to perceptual asymmetry, where participants hold asymmetric partial information and the same referring expression yields different denotations depending on whose information state grounds the reference. We evaluate this through cross-corpora analysis and LLM probing on referentially asymmetric dialogue tasks, primarily the HCRC MapTask (Anderson et al., 1991). We find that FPO's friction functional is empirically valid only when evaluated from within each participant's information hori
arXiv:2606.30957v1 Announce Type: new Abstract: Managing our emotional responses to events is key to emotional well-being, a process referred to as emotion regulation in psychology. Previous work has established that the degree to which we distance events is a type of emotion regulation. When we psychologically distance from events there can be markers in our language. These markers have been referred to as linguistic distancing. We build upon a previous metric to operationalize linguistic distancing, and explore how it changes across the lifespan. We explore this systematically by analyzing large amounts of social media text, a venue where people express their emotions. By investigating how distancing varies across age groups we can better understand how emotion regulation varies with age and provide initial benchmarks on social media data. We provide additional evidence further strengthening the hypothesis that linguistic distancing occurs in proportionally more instances with age. T
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these communities, which affects international collaboration and the progress of sustainability-related research. We present a benchmark for Arabic--Russian scientific translation. The benchmark includes a hybrid parallel corpus of about 27,000 sentence pairs, compiled from scientific abstracts and general-domain texts (religion, news, conversations). We fine-tune three multilingual language models -- mT5-base (580M parameters), NLLB-200-distilled-1.3B (1.3B), and Qwen2.5-7B-Instruct (7B) -- using LoRA with ranks 8, 16, 32, and 64. The Qwen2.5-7B model with QLoRA (rank 8) yields BLEU 23.15, chrF 43.89, BERTScore 0.906, and COMET 0.758. These are +4.36 BLEU and +0.051 COMET above the zero-shot baseline. Few-shot prompting with three examples does not improve performance, indicating that domain-spec
arXiv:2606.30914v1 Announce Type: new Abstract: Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Llama 3 and Gemma 3). Our results reveal a clear architectural trade-off: encoder models achieve higher performance on clean text but degrade substantially under noise, whereas decoder-only LLMs are markedly more robust, particularly when event triggers are corrupted. We further show that embedding annotation guidelines during instruction tuning establ
arXiv:2606.30887v1 Announce Type: new Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric. We introduce a framework that formulates therapeutic response generation as a decision-refinement problem driven by multi-dimensional, human-aligned evaluation. In Stage I, we introduce TheraJudge, an open-source therapeutic evaluator trained via preference-based optimization on human-annotated data to produce reliable judgments across 7 psychological dimensions. In Stage II, we introduce TheraAgent, which operationalizes TheraJudge's evaluations through a coordinated refinement process with specialized Critic, Coach, and Therapist roles that translate evaluative signals into targeted response revisions. Empirically, TheraJudge achieves strong agreement with clinician ratings, with intraclass correlation coefficients (ICC = 0.87-0.95), surpassing supervi
arXiv:2606.30857v1 Announce Type: new Abstract: This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all three subtasks: binary polarization detection, polarization type classification, and manifestation identification for English and Swahili. Our approach leverages transformer-based models (RoBERTa-base for English, AfroXLMR-base for Swahili) with class-weighted loss functions to address severe label imbalance and per-label threshold tuning to optimize multi-label classification. On the test set, we achieve F1 macro scores of 0.7901 (English) and 0.7910 (Swahili) for Subtask 1, 0.4615 (English) and 0.4808 (Swahili) for Subtask 2 and 0.4791 (English) and 0.5830 (Swahili) for Subtask 3, which give competitive performance on the leaderboard, demonstrating the effectiveness of our methods for handling imbalanced multi-label polarization detection. Our error analysis reveals that models struggle
arXiv:2606.30851v1 Announce Type: new Abstract: Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL. Common test-time inference strategies, including Best-of-N sampling and Majority Voting, rely on heuristic signals such as execution success or output frequency, which provide limited semantic discrimination across candidate outputs. In this work, we study Outcome Reward Models (ORMs) as learned semantic scoring functions for test-time verification in Text-to-SQL. While ORMs have been previously explored for test-time scaling and alignment, their application to structured query generation remains underexplored. We introduce GradeSQL, a scalable framework for training task-specific ORMs via automated candidate generation and execution-based labeling, enabling verifier training without manual annotation. We integrate ORMs into a verification-driven Best-of-N pipeline and evaluate our approach
arXiv:2606.30815v1 Announce Type: new Abstract: Recent work suggests that transformer language models show a bias towards human languages over unnatural ("impossible") languages argued to be unacquirable by humans. However, this literature has largely based these claims on differences in sample efficiency and test-set perplexity, rather than on direct evaluations of the linguistic capacities that could plausibly explain non-attestation in human languages. We evaluate two theoretically motivated linking hypotheses: impossibility arising from deficiencies in grammatical sensitivity or generative production. Using GPT-2 style models trained on perturbed "impossible" variants of English, we measure sensitivity to grammaticality using BLiMP minimal pairs, finding that model performance exhibits only gradual degradation, mediated by the language's information locality. In contrast, these models exhibited pronounced failures in generation, producing substantially fewer high-quality sentences
arXiv:2606.30814v1 Announce Type: new Abstract: Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global calibration metrics such as Expected Calibration Error and Brier Score. We begin by showing, both theoretically and empirically, that such comparisons are confounded by differences in model accuracy. For fairer cross-model comparison, we then propose ACE, an accuracy-controlled evaluation framework with three complementary views: Instance-Aligned, Distribution-Aligned, and Candidate-Aligned calibration. Across multiple benchmarks, model families, and confidence elicitation methods, we use ACE to study two practically important comparison axes, small versus large models and thinking versus non-thinking models. We find that many previously reported calibration advantages under raw global metrics weaken substantially after accuracy control. We also find that rankin
arXiv:2606.30790v1 Announce Type: new Abstract: Romanized Code Mixing (RCM), where bilingual speakers fluidly blend local languages with English in Roman script, has emerged as the dominant form of communication across multilingual communities. While Large Language Models (LLMs) perform strongly on monolingual and native-script benchmarks, their ability to follow instructions and reason over RCM-based content remains largely unexplored. To this end, we introduce the Indi-RomCoM benchmark for facilitating systematic evaluation on Indic Romanized Code-Mixed instructions. Our benchmark spans seven instruction-following tasks, four widely spoken Indic languages, and three controlled code-mixing intensity levels. We extensively evaluate a suite of LLMs covering proprietary, open-weight, and Indic-focused models under zero- and few-shot settings. LLMs consistently underperform on RCM instructions, with performance degrading as code-mixing density increases. Furthermore, reasoning tasks suffe
arXiv:2606.30775v1 Announce Type: new Abstract: Enterprise AI agents route user queries to specialized skills by matching queries against natural language skill descriptions. When two skills share overlapping descriptions, the routing LLM misroutes queries, a failure we term skill collision. As agents scale to dozens of skills, manually tuning descriptions to maintain routing accuracy becomes a significant engineering bottleneck. We deploy an automated description optimization pipeline on a production enterprise group chat agent (9 skills, 372 regression cases). The pipeline produces descriptions averaging 79.2% F1, matching manually tuned descriptions at 79.4% F1 (average per-skill difference -0.20%, within the 0.78% multi-seed noise floor), while reducing per-skill engineering effort from 120 minutes to 3.8 minutes (32 times speedup). We then examine which pipeline components actually drive this match. Systematic ablation on both the production system and ToolBench (16k tools) reveal
arXiv:2511.00810v4 Announce Type: replace-cross Abstract: Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs exhibit native grounding ability embedded in their attention maps, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user in
arXiv:2606.02301v2 Announce Type: replace Abstract: Chronic pain diminishes quality of life by decreasing functional ability, yet objectively measuring this functional impact remains challenging in real-world settings. While optical motion capture provides high precision for assessing altered movement quality, it is costly and restricted to laboratory environments. We aimed to develop and validate Quantitative Movement Testing (QMT), a computer vision pipeline extracting 3D kinematic biomarkers from standard monocular smartphone video, balancing clinical accessibility with biomechanical accuracy. We validated the QMT pipeline, utilising deep learning-based 3D pose-estimation, against gold-standard optical motion capture in healthy controls (N=13). Following leave-one-subject-out calibration to correct systematic bias, we deployed QMT in two prospective clinical cohorts to assess real-world utility: a pre- and post-intervention trial for fibromyalgia patients, and a 30-day longitudinal
arXiv:2604.18121v2 Announce Type: replace Abstract: When an individual is harmed by someone in power, such as a workplace manager, it can help to identify allies--people who would offer sympathy, advice, or supportive action. However, ally discovery is fraught because the very people who might be most relevant--e.g., someone who reports to the same manager--might not be sympathetic and could potentially exacerbate the harm. We examine this problem in the specific context of PhD students navigating advising challenges and present a social media platform called "Moa" that brings together a number of features that we believe facilitate ally discovery. Moa's most novel element is an audience selection process that uses what we call consent boundaries, which allow users to flexibly define each post or comment's audience based on factors such as common social identity or lived experience, all while preserving anonymity--neither senders nor recipients learn each other's identities, even as th
arXiv:2509.19957v2 Announce Type: replace Abstract: Visual impairments present significant challenges to individuals worldwide, impacting daily activities and quality of life. Visual neuroprosthetics offer a promising solution, leveraging advancements in technology to provide a simplified visual sense through devices comprising cameras, computers, and implanted electrodes. This study investigates user-centered design principles for a phosphene vision algorithm, utilizing feedback from visually impaired individuals to guide the development of a gaze-controlled semantic segmentation system. We conducted interviews revealing key design principles. These principles informed the implementation of a gaze-guided semantic segmentation algorithm using the Segment Anything Model (SAM). In a simulated phosphene vision environment, participants performed object detection tasks under SAM, edge detection, and normal vision conditions. SAM improved identification accuracy over edge detection, remaine
arXiv:2508.02376v2 Announce Type: replace Abstract: Embodied conversational agents (ECAs) are increasingly more realistic and capable of dynamic conversations. In online surveys, anthropomorphic agents could help address issues like careless responding and satisficing, which originate from the lack of personal engagement and perceived accountability. However, there is a lack of understanding of how ECAs in user experience research may affect participant engagement, satisfaction, and the quality of responses. As a proof of concept, we propose an instrument that enables the incorporation of conversations with a virtual avatar into surveys, using on AI-driven video generation, speech recognition, and Large Language Models. In our between-subjects study, 80 participants (UK, stratified random sample of general population) either talked to a voice-based agent with an animated video avatar, or interacted with a chatbot. Across surveys based on two self-reported psychometric tests, 2,265 conv
arXiv:2606.31211v1 Announce Type: cross Abstract: We present AA, a multi-view multimodal dataset for screen-based gaze estimation. The dataset captures synchronized facial observations from eight fixed screen-mounted cameras and two additional side-view cameras, paired with precise screen-space gaze targets collected under controlled fixation conditions. Each sample contains multi-view face observations together with structured facial region crops, enabling multimodal learning from both global and local visual cues. Unlike existing single-view gaze datasets, AA provides multi-view coverage from both screen-mounted and side-mounted perspectives, enabling more robust modeling under viewpoint variation and occlusion. The dataset includes subject-independent evaluation splits and a standardized data processing pipeline to support reproducible research in gaze estimation.
arXiv:2606.31112v1 Announce Type: cross Abstract: ASR systems have been often reported to underperform on atypical speech. An often conflated compounding factor is the existence of two valid transcription references: verbatim (actual produced speech, including repetitions/prolongations) and intended (the canonical form of the text with disfluencies removed) in atypical speech recognition depending on context and use-case. Most ASR evaluations conflate this duality into a single ground truth and reward systems that delete disfluencies, ignoring verbatim faithfulness. We benchmark 11 ASR models from encoder-decoder, CTC and transducer families using both verbatim and intended references on atypical stuttered speech as a case study. Our quantitative assessment underlines the disparity in model performance and rankings using the two transcript styles. Through this analysis, we highlight the importance of selecting a suitable transcription reference for valid model selection depending on th
arXiv:2606.31069v1 Announce Type: cross Abstract: Up to this point, keyword extraction task typically relies solely on textual data. Neglecting visual details and audio features from image and audio modalities leads to deficiencies in information richness and overlooks potential correlations, thereby constraining the model's ability to learn representations of the data and the accuracy of model predictions. Furthermore, the currently available multimodal datasets for keyword extraction task are particularly scarce, further hindering the progress of research on multimodal keyword extraction task. Therefore, this study constructs a multimodal dataset of academic paper consisting of 1000 samples, with each sample containing paper text, images, audios and keywords. Based on unsupervised and supervised methods of keyword extraction, experiments are conducted using textual data from papers, as well as text extracted from images and audio. The aim is to investigate the differences in performa
arXiv:2606.31762v1 Announce Type: new Abstract: Minority viewpoints are often suppressed in power-imbalanced group decision-making due to social pressure to comply with the majority. To address this problem, we developed an LLM-powered dissenting minority support system that aimed to foster attention to minority views through either AI-generated counterarguments or AI-mediated messages. We conducted a mixed-method experiment with 96 participants in 24 groups, comparing minority members' experiences across baseline, AI-counterargument, and AI-mediated message conditions. Our findings revealed a nuanced trade-off: AI-generated counterarguments fostered a more flexible atmosphere and enhanced satisfaction, while AI-mediated messaging increased minority participation but unexpectedly reduced their psychological safety. This research contributes empirical evidence on how different AI implementations affect group dynamics, identifies a critical support paradox between participation and psych
arXiv:2606.31311v1 Announce Type: new Abstract: Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype. We describe a case where a workflow language and an AI assistant reduced this effort to one afternoon. The idea under test: relax the Pareto frontier with a tolerance and group the surviving options into recurring types -- ``constellations'' on a ``soft sky''. Using the Artifact--Transform Workflow Language (ATWL) as a scaffold, we obtained a consistent workflow in minutes and a running prototype in a few hours. We derive three lessons. The scaffold matters: without ATWL the assistant produced a naive workflow. The scaffold alone is not enough: the first implementation was only average, and expert knowledge injection was needed to reach state-of-the-art quality. Finally, the way the scaffold is used matters: controlled experiments show that a language definition and a library of examples suppo
arXiv:2606.31012v1 Announce Type: new Abstract: While large language models now enable rapid generation of interactive learning materials, evaluating the interaction quality of these explorable explanations remains an open challenge. Existing benchmarks largely focus on code executability or visual fidelity, providing limited insight into dynamic interaction behaviors such as learner-controlled state transitions and context-sensitive system responses, which are factors that critically shape learners' conceptual understanding. We present EE-Eval, an automated evaluation framework that formalizes interactivity as a finite space of learner-controllable states and transitions, represented as a Finite State Machine (FSM). By extracting FSMs from AI-generated explorable explanations, EE-Eval externalizes implicit interaction logic into an explicit, machine-interpretable graph. Evaluation is performed by comparing each generated FSM to an ideal FSM that encodes pedagogical intent, using a com
arXiv:2606.30980v1 Announce Type: new Abstract: Semi-structured interviews rely on timely, context-sensitive follow-up questions, yet interviewers' cognitive load and limited domain familiarity can constrain probing depth. We report findings from an LLM-in-the-loop Wizard-of-Oz (WoZ) study that simulates an AI follow-up assistant in live interviewing while preserving human oversight. In our setup, a co-interviewer selectively relayed and could edit AI-generated follow-up questions (AGQs) produced in real time by GPT-4o, enabling a realistic approximation of deployment without fully automating the interaction. Across 17 interviewers with varied qualitative-method expertise, participants raised five interlocking concerns: (1) harmful or discriminatory language and unpredictable interaction harms, (2) undermining interviewees' sense of respect through divided attention and missing nonverbal cues, (3) technology-based participation inequality, (4) unclear responsibility when harms occur, a
arXiv:2606.30884v1 Announce Type: new Abstract: Visualization has been recognized as a valuable means of supporting debugging by externalizing runtime behavior that would otherwise remain hidden or scattered. However, most visual debugging research has focused on traditional software development settings, leaving the distinct challenges of data-intensive workflows largely uncharacterized. To build visual debugging support for these settings, we first need to characterize how practitioners debug in these settings and translate their challenges into concrete visualization opportunities. To this end, we conducted semi-structured interviews with nine participants from diverse data-intensive domains and analyzed the data using thematic analysis. Our analysis reveals three cross-cutting challenge: assembling fragmented evidence, detecting expected-observed discrepancies, and tracing state evolution across workflow components. We distill these challenges into three concrete requirements that
arXiv:2606.30879v1 Announce Type: new Abstract: Accurately assessing a programmer's skill level is critical for hiring, team composition, and performance evaluation in the software industry. Conventional methods, such as coding tests or interviews, often fail to capture the full spectrum of cognitive abilities underlying programming expertise. This study explores using electroencephalography (EEG) and machine learning to investigate neural correlates of programming skill. We analyzed an existing EEG dataset recorded during code comprehension from 37 programmers with 1 to 30 years of experience (8.1 +/- 6.3 years) to examine relationships between neural activity and expertise. Additionally, we conducted classification experiments using Random Forest classifiers with diverse features for binary (experts vs. novices) and multi-class (experts, intermediates, novices) setups.We identified EEG features and brain regions associated with programming expertise. Specifically, EEG entropy showed
arXiv:2606.30828v1 Announce Type: new Abstract: While there's optimism around medical AI tools due to their abilities to adapt from user-to-user and across environments, these new abilities complicate how people and organizations are able to predict and manage risk based on existing laws and regulations. Lawyers are trained to identify potential legal outcomes, but they lack technical AI knowledge, making it difficult to translate their expertise to creators and users of AI tools. We contribute insights from our co-design process with U.S. lawyers to identify and translate ways to predict and manage risks of medical AI tools. We present the visualizations we developed through two years of cross-disciplinary efforts and thereby illustrate our findings about how legal risks are determined and our strategies for people and organizations to predict and manage these risks. We offer insights about leveraging lawyers' expertise to understand, predict, and manage legal risks.
arXiv:2606.30824v1 Announce Type: new Abstract: We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress and longitude thematic deviation. Land features are recovered from document density via kernel density estimation and labeled by theme. A narrative trail built from the underlying narrative coherence graph, and constrained to be monotone in geodesic progress, provides a readable storyline. The projection's axes are semantically grounded in the user's chosen narrative endpoints, and the globe metaphor affords rotation and antipodal reading. We demonstrate the method on a 540-article Cuban Protests corpus, showing a storyline from Obama's 2016 visit to the 2021 International Aid during the protests.
arXiv:2606.21880v2 Announce Type: replace-cross Abstract: Has generative AI changed how labor markets value human capital? We study this question using contract-level data from Upwork, a large online labor market. We represent worker profiles with high-dimensional text embeddings, allowing us to capture rich human capital information from unstructured profile text. We then compute the predictive importance of workers' human capital information and posted hourly rates for client demand, and incorporate these measures into a difference-in-differences design around the release of ChatGPT. We find that in more AI-exposed job categories, the importance of human capital declines and the importance of price rises, suggesting a commoditization effect of AI on labor. Two additional findings support commoditization as a mechanism: The demand premium enjoyed by workers with strong human capital declines in more AI-exposed categories, and demand reallocates toward lower-priced workers. Our results
arXiv:2605.29444v2 Announce Type: replace-cross Abstract: Determining a linear utility function that correlates with observed candidate rankings is a foundational problem with applications in domains such as admissions, hiring, and recommendation systems, e.g., [Storandt and Funke, AAAI'19, Zhang et al., KDD'23, Wang et al., ICDE'24 (best paper award), Chen and Wong, VLDB'24]. Traditionally, these models assume full visibility into the feature sets used to determine the utility score. However, real-world scenarios often involve sensitive attributes that are hidden or partially observed, yet may influence outcomes through additive bonuses designed to promote fairness, as in [Gale and Marian, ICDE'24]. Motivated by such practical concerns, we study a variant of the ranking explanation problem where sensitive features are unobserved but may influence candidate rankings through group-specific linear boosts. We present a formal framework for modeling this problem and develop an algorithmic
arXiv:2404.01356v4 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Ro
arXiv:2603.11001v3 Announce Type: replace Abstract: Human uplift studies, or studies that measure the effects of AI access on human performance via randomized controlled trials (RCT) or similar methodologies, increasingly inform frontier AI governance and deployment decisions. While RCT methods are robust in other fields, their interaction with the distinctive properties of frontier AI systems remains underexamined, particularly when results are used to inform high-stakes decisions. We present findings from interviews with 16 expert practitioners with experience conducting human uplift studies in domains including biosecurity, cybersecurity, education, and labor. Across interviews, experts described a recurring tension between the standard causal inference assumptions upon which human uplift studies rely and the object of study itself. Rapidly evolving AI systems, shifting baselines, heterogeneous and changing user proficiency, and porous real-world settings strain assumptions underlyi
arXiv:2601.16398v3 Announce Type: replace Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior only through input-output testing. These methods are limited to tests constructed in the input space, often generated by heuristics. In addition, many socially relevant model properties (e.g., gender bias) are abstract and difficult to measure through text-based inputs alone. To address these limitations, we propose a white-box sensitivity auditing framework for LLMs that leverages activation steering to conduct more rigorous assessments through model internals. Our auditing method conducts internal sensitivity tests by manipulating key concepts relevant to the model's intended function for the task. We demonstrate its application to bias audits in four simulated high-stakes LLM decision tasks. Our me
arXiv:2512.05929v4 Announce Type: replace Abstract: This study addresses categories of harm surrounding Large Language Models (LLMs) in the field of artificial intelligence. It addresses five categories of harms addressed before, during, and after development of AI applications: pre-development, direct output, Misuse and Malicious Application, and downstream application. By underscoring the need to define risks of the current landscape to ensure accountability, transparency and navigating bias when adapting LLMs for practical applications. It proposes mitigation strategies and future directions for specific domains and a dynamic auditing system guiding responsible development and integration of LLMs in a standardized proposal.
arXiv:2508.15516v3 Announce Type: replace Abstract: Urban parks support public health, but landscape architecture typically examines them through form and function. Prior equitable access research focused on park form, while functional studies relied on small-scale surveys, movement data, or broad usage metrics, missing specific activities and visit motivations. This gap limits our grasp of parks' functional diversity. We address this with a novel method refining mobile base station coverage via antenna azimuths to isolate park-specific traffic from surroundings. Using Paris as a case study, we process 492 million hourly per-app mobile records (35% market share) from 45 urban parks. We test the central-city hypothesis (multifunctional parks in dense, high-rent zones due to land constraints) and socio-spatial hypothesis (parks reflecting neighborhood routines and preferences). Results reveal parks' unique mobile traffic signatures, distinct from urban contexts and each other. Clustering
arXiv:2503.05785v2 Announce Type: replace Abstract: Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching. Empirical data on how students perceive the increasing influence of AI, which different types of tools they use, what they expect from them in their daily academic tasks, and their concerns regarding the use of AI in their studies are still limited. The manuscript presents findings from a quantitative survey conducted among sports students of all semesters in Germany using an online questionnaire. It explores aspects such as students' usage behavior, motivational factors, and uncertainties regarding the impact of AI tools on academia in the future. Furthermore, the social climate in sports studies is being investigated to provide a general overview of the current situation of the students in Germany. Data collection took place between August and November 2023, addressing all sports departments at G
arXiv:2606.31644v1 Announce Type: cross Abstract: As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behaviors are genuine or superficial. We show that current fairness evaluations substantially overestimate moral safety. Models appear fair when demographic identity is stated as an explicit label, yet become measurably less fair when the same identity must be inferred. We term this failure \emph{performative compliance}, where a model is fair when the presentation resembles a fairness evaluation and less fair as that cue weakens. We introduce a cue-variation methodology that holds the moral dilemma and the demographic identity fixed and varies only how that identity is conveyed. Hiding the explicit label raises harmful decisions by $+4.4$~pp and changes model safety rankings, and the shift persists when models correctly infer the demographic, ruling out attribution error. We propose the \textb
arXiv:2606.31590v1 Announce Type: cross Abstract: Digital sovereignty (DS) is an increasingly important concept and political agenda throughout the world, including in the European Union (EU). However, the concept is also regrettably vague. With this critical point in mind, the paper presents an analysis of digital sovereignty as a quality attribute for software architectures in the context of cloud computing and the EU's policy frameworks for it. The analysis reveals that DS can be sharpened analytically by conceptualizing it as a quality attribute. The analysis further demonstrates how DS satisfies many of the classical properties of quality attributes for software architectures, including their measurability and validation, the trade-offs they involve, and the scenario-based methodology commonly used for analyzing them.
arXiv:2606.31270v1 Announce Type: cross Abstract: Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and versatility. A major challenge in developing these agents is collecting large-scale, high-quality trajectories. The standard approach generates synthetic data through a self-improving loop: an agent is placed in a verifiable environment and iteratively fine-tuned on its successful trajectories. Despite its effectiveness, this paradigm exploits only successful trajectories and discards the failed ones, even though failures carry rich information about a model's weaknesses. In this work, we explore a complementary failure-driven self-improvement loop, a data-centric paradigm that turns failed trajectories into agent improvements. Specifically, we employ an LLM to diagnose failure modes, propose inference-time solutions, and generate code patches -- lightly verified