February 2026

arXiv:2602.04031v1 Announce Type: new Abstract: Tabular Language Models (TLMs) have been claimed to achieve emergent generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM, utilizing 165 datasets from the UniPredict benchmark. Our investigation reveals three findings. First, binary and categorical classification achieve near-zero median lift over majority-class baselines and strong aggregate performance is driven entirely by quartile classification tasks. Second, top-performing datasets exhibit pervasive contamination, including complete train-test overlap and task-level leakage […]

Ver mais

arXiv:2602.04030v1 Announce Type: new Abstract: Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character dependencies, but they overlook the benefits of external linguistic knowledge. Prior attempts to integrate language models either adapt language modeling objectives without external knowledge or apply pretrained models that are misaligned with the word-level granularity of scene text. We propose […]

Ver mais

arXiv:2602.04029v1 Announce Type: new Abstract: Relational Foundation Models (RFMs) facilitate data-driven decision-making by learning from complex multi-table databases. However, the diverse relational databases needed to train such models are rarely public due to privacy constraints. While there are methods to generate synthetic tabular data of arbitrary size, incorporating schema structure and primary–foreign key connectivity for multi-table generation remains challenging. Here we introduce PluRel, a framework to synthesize multi-tabular relational databases from scratch. In a step-by-step fashion, PluRel models […]

Ver mais

arXiv:2602.04028v1 Announce Type: new Abstract: Explaining autonomous and intelligent systems is critical in order to improve trust in their decisions. Counterfactuals have emerged as one of the most compelling forms of explanation. They address “why not” questions by revealing how decisions could be altered. Despite the growing literature, most existing explainers focus on a single type of counterfactual and are restricted to local explanations, focusing on individual instances. There has been no systematic study of alternative counterfactual types, […]

Ver mais

arXiv:2602.04027v1 Announce Type: new Abstract: This work presents a consensus-based Bayesian framework to detect malicious user behavior in enterprise directory access graphs. By modeling directories as topics and users as agents within a multi-level interaction graph, we simulate access evolution using influence-weighted opinion dynamics. Logical dependencies between users are encoded in dynamic matrices Ci, and directory similarity is captured via a shared influence matrix W. Malicious behavior is injected as cross-component logical perturbations that violate structural norms of […]

Ver mais

arXiv:2602.04026v1 Announce Type: new Abstract: Open source software ecosystems are composed of a variety of stakeholders including but not limited to non-profit organizations, volunteer contributors, users, and corporations. The needs and motivations of these stakeholders are often diverse, unknown, and sometimes even conflicting given the engagement and investment of both volunteers and corporate actors. Given this, it is not clear how open source communities identify and engage with their stakeholders, understand their needs, and hold themselves accountable to […]

Ver mais

arXiv:2602.04023v1 Announce Type: new Abstract: Generative AI blurs the lines of authorship in computing education, creating uncertainty around how students should attribute AI assistance. To examine these emerging norms, we conducted a factorial vignette study with 94 computer science students across 102 unique scenarios, systematically manipulating assessment type, AI autonomy, student activity, prior knowledge, and human refinement effort. This paper details how these factors influence students’ perceptions of ownership and disclosure preferences. Our findings indicate that attribution judgments […]

Ver mais

arXiv:2602.04019v1 Announce Type: new Abstract: As large language models (LLMs) continue to grow, the cost of full-parameter fine-tuning has made parameter-efficient fine-tuning (PEFT) the default strategy for downstream adaptation. Constraints from inference latency in scalable serving and fine-tuning cost in edge or rapid-deployment settings make the choice of which layers to fine-tune unavoidable. Yet current practice typically applies PEFT uniformly across all layers, with limited understanding or leverage of layer selection. This paper develops a unified projected residual […]

Ver mais

arXiv:2602.04017v1 Announce Type: new Abstract: Despite growing recognition that responsible AI requires domain knowledge, current work on conversational AI primarily draws on clinical expertise that prioritises diagnosis and intervention. However, much of everyday emotional support needs occur in non-clinical contexts, and therefore requires different conversational approaches. We examine how chaplains, who guide individuals through personal crises, grief, and reflection, perceive and engage with conversational AI. We recruited eighteen chaplains to build AI chatbots. While some chaplains viewed chatbots […]

Ver mais

arXiv:2602.04015v1 Announce Type: new Abstract: Virtual collaboration has transformed how people in mixed-ability teams, composed of disabled and non-disabled people, work together by offering greater flexibility. In these settings, accessibility practices, such as accommodations and inclusive norms, are essential for providing access to disabled people. However, we do not yet know how these practices shape broader facets of teamwork, such as productivity, participation, and camaraderie. To address this gap, we interviewed 18 participants (12 disabled, 6 non-disabled) who […]

Ver mais