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:2605.08093v2 Announce Type: replace Abstract: The use of chatbots for various forms of companionship is growing rapidly, raising a myriad of questions about simulated relationships, emotional dependence, and psychological harm. While major platforms such as ChatGPT, Grok, and Character AI are the subject of a growing body of research and legal inquiries, apps explicitly built for simulating intimate interpersonal relationships remain under-explored. In this work, we evaluate the five most popular AI companion mobile applications for factors that encourage parasocial interaction and may manipulate users. We do this by manually annotating the user experience each offers. Specifically, we systematically record and quantify design dark patterns, anthropomorphism, stereotypes, erotica, and technical performance issues. We find that all apps contain substantial dark patterns aimed at increasing monetisation and user engagement. Erotica and gamification such as levelling are also preval
arXiv:2608.07446v1 Announce Type: cross Abstract: Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to production, manual harm identification and mitigation are becoming difficult to scale. Although many tools support model evaluation, adversarial testing, runtime guardrails, and observability, the tooling landscape remains fragmented. Tools are typically designed for specific engineering tasks and described in technical terms that do not align with governance frameworks or risk taxonomies, making it difficult to determine which tools address which risks and where critical gaps remain. This paper proposes a structured protocol to automate AI risk mitigation through a taxonomy-driven analysis of open-source LLM evaluation and security tools. We map the capabilities of 21 prominent open-source tools to the 32 subcategories of the extended MIT AI Risk Mitigation an
arXiv:2608.07364v1 Announce Type: cross Abstract: Contribution: This paper presents a six-phase AI-assisted instructional design architecture based on the Curriculum as Code paradigm, integrating Generative AI with LaTeX and Python to automate the creation of reproducible, visually consistent, and technically precise materials for STEM education. Background: Creating customized instructional materials for active learning imposes a heavy workload on faculty. Standard presentation tools lack robust support for technical content, while current AI applications often hallucinate and fail to formalize the instructional authoring process, limiting their utility for rigorous academic design. Intended Outcomes: The framework aims to reduce preparation time while ensuring mathematical accuracy, adherence to institutional visual identity, and preservation of the instructor's tacit pedagogical knowledge through explicit rules. Application Design: The solution comprises a six-phase pipeline that re
arXiv:2608.07069v1 Announce Type: cross Abstract: AI assistants are becoming a primary interface for local discovery, yet almost nothing is known about which venues they surface -- especially in food and drink, where recommendations carry direct revenue consequences. We present the first census-denominated audit of AI venue recommendation: a complete enumeration of 4,776 cafes, restaurants, and bars across two bounded markets (Canggu and Ubud, Bali), against which we evaluate 2,208 search-grounded responses from four production AI systems (ChatGPT, Claude, Gemini, Perplexity) to 96 persona-conditioned queries, collected over seven days under a pre-registered protocol. Because we observe the full market, we can measure what sampled audits cannot: 85.6% of venues were never recommended by any system -- 72.6% even among established venues with fifty or more ratings. Visibility follows a two-margin structure. Entry into answers is associated with documentation: review volume (OR 1.64), an
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language models, we designed a circular-synchronization experiment applying a state-encoding intervention while holding the physical system fixed: each agent sees only a summary of its neighbours' relative phases and chooses to advance, stay or retard. Encoding that state as low-order circular moments rather than as a histogram selected different collective outcomes. In GPT the moment encoding synchronized the population in 6/6 seeds and the histogram encodings in 0/6; the effect replicated in Claude but reversed direction. Replaying identical fields shifted each agent's advance/stay/retard probabilities far beyond within-encoding repeat variation, in GPT, Claude and Gemini; in GPT, presentation alone shifted the operator with the moment values fixed. State encodings therefore form part of a model-depe
arXiv:2608.06955v1 Announce Type: cross Abstract: Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more. Yet whether LLMs systematically reproduce evaluative hierarchies remains unclear. Prior research on cultural bias in LLMs suggests competing expectations: models may mirror the popularity signals of internet texts, or may reproduce forms of prestige embedded in critical discourse. We probe this question through a study of film evaluations with eight models from four families (Anthropic, OpenAI, Alibaba, and Mistral), using a 200-film benchmark partitioned into critically acclaimed, commercially successful, and dual-legitimacy (critical acclaim + commercial success) films. Across 20,000 pairwise forced-choice comparisons per model analyzed with Bradley--Terry estimation, we observe a consistent critical acclaim orientation with all models: critically acclaimed yet commercially obscure films are selected over
arXiv:2608.06908v1 Announce Type: cross Abstract: We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT). WEAT is a bias measurement method widely used in both computational social science and AI fairness research. It relies on cosine similarity as a measure of semantic association, which assumes that the embedding space is approximately isotropic. However, prior work has reported that many widely used language models do not satisfy this assumption, raising concerns about the reliability of bias measurements. ZCA whitening transforms the covariance of the embedding space into the identity matrix while minimizing perturbation to the original vectors. This transformation restores the isotropy condition on which WEAT relies. We evaluate our approach on ten standard WEAT test suites and seven models spanning three architectural families, yielding 70 model-task combinations. The results show that ZCA whiteni
arXiv:2608.06549v1 Announce Type: cross Abstract: LLMs are increasingly being applied to tasks involving institutional and political texts, but existing benchmarks evaluate them on isolated documents or single tasks. In realpolitik, negotiations are longitudinal data, where participating parties can align or argue over multiple iterations and each turn is an outcome of the previous turns, hence, understanding one turn requires tracking everything before it. We introduce TradeVerse, a benchmark built from the World Trade Organisation (WTO) specific trade concerns, where member states challenge one another and exchange arguments over multiple rounds, sometimes for years. We, in TradeVerse, reconstruct minutes of $1170$ meetings, spanning across 5 groups and $89$ product groups and define three tasks: first, the system has to analyze the longitudinal meeting records and predict the harmonized system codes (HS chapters) of the products under discussion in the particular meeting, second, we
arXiv:2512.07901v3 Announce Type: cross Abstract: Von Neumann founded both game theory and the theory of self-reproducing automata, but the two programs never merged. This paper provides the synthesis. The Theory of Strategic Evolution analyzes strategic replicators: entities that optimize under resource constraints and spawn copies of themselves. We introduce Games with Endogenous Players (GEPs), where lineages (not instances) are the fundamental strategic units, and define Evolutionarily Stable Distributions of Intelligence (ESDIs) as the resulting equilibrium concept. The central mathematical object is a hierarchy of strategic layers linked by cross-level gain matrices. Under a small-gain condition (spectral radius less than one), the system admits a global Lyapunov function at every finite depth. We prove closure under meta-selection: adding governance levels, innovation, or constitutional evolution preserves the dynamical structure. The Alignment Impossibility Theorem shows that u
arXiv:2608.07452v1 Announce Type: new Abstract: Artificial intelligence-based solutions offer new efficiency-increasing possibilities in many applications, including credit scoring. Yet, the increasing sophistication of machine-learning models in use raises concerns regarding many of their aspects, explainability notwithstanding. We review the relevant EU legal background and integrate this review with insights from technical sciences to interpret relevant legal provisions in the light of technological possibilities. We reject the narrow interpretations of the right to explanation and suggest the broad one, which encompasses not only a technical explanations but also a legal justification as the only one that allows to safeguard the creditors rights in an operative manner.
arXiv:2608.07337v1 Announce Type: new Abstract: The arrival of generative AI as a cheap, widely accessible commercial service, and the tidal wave of AI-generated synthetic content it has unleashed, have provoked deep epistemic and social anxieties and raised difficult governance questions that policymakers are struggling to address. One approach that has attracted both enthusiasm from regulators and skepticism from researchers is digital watermarking. Signals embedded in a synthetically-generated piece of content indicating that it was AI-generated---possibly even identifying the specific systems that generated it---appear to offer a path toward mitigating risks of genAI that avoids the downsides of more interventionist strategies. But critics warn that watermarks may prove technically brittle, epistemically ambiguous, and politically ineffectual tools. In this paper, we explore the challenges and opportunities of using digital watermarking for AI governance, paying special attention t
arXiv:2608.07297v1 Announce Type: new Abstract: Modern AI systems depend on annotated data, but annotation is rarely treated as the act of measurement that it is. Instead, annotation quality is commonly reduced to agreement: if multiple annotators assign the same annotation to a data instance, the annotations are taken to be high-quality. Yet agreement does not establish whether annotations validly capture the underlying concept they are meant to represent. In this paper, we argue that data annotation should be understood as a measurement problem. Like other forms of measurement, annotation requires defining a concept, operationalizing it through an instrument, applying that instrument, and evaluating the reliability and validity of the resulting measurements. Drawing on a literature review of annotation quality research (N=132) and semi-structured interviews with annotation team members (N=10), we develop a framework for diagnosing and correcting annotation issues. First, we map key d
arXiv:2608.06932v1 Announce Type: new Abstract: Educational short-video research spans disciplines, platforms and learning contexts, but the same label is applied to resources differing in function, activity, context and evaluation, complicating comparison and evidence synthesis. This study mapped the development, thematic organisation and operationalisation of educational short-video research. We analysed 2,169 records indexed in Web of Science and Scopus up to 11 June 2026 using bibliometric analysis, non-negative matrix factorisation topic modelling and structured content analysis. Publication output increased sharply from the mid-2010s but remained dispersed across outlets. Among 16 first-level topics, Skill Development in Educational Contexts was the largest, forming the structural core of the field, while topic overlap was predominantly pairwise. Video-Based Health Interventions for Attitude Change and Cognitive Load and Engagement in Instructional Video Design combined positive
arXiv:2608.06903v1 Announce Type: new Abstract: The rapid growth of artificial intelligence (AI) in music has expanded research from generation and information retrieval to education, health, and governance. Yet this growth does not necessarily imply balanced research attention. Where is research attention directed across diverse music tasks, and how can such imbalance be systematically measured? Existing studies examine AI music from separate technical, application-specific, or bibliometric perspectives, but lack a systematic framework for measuring field-level imbalance. To address this gap, we analyze 6,839 AI music publications from 2015 to April 2026 using a joint taxonomy of 12 application categories and 11 technical method families. We propose the Research Attention Profile, comprising four indicators of technical investment, method allocation, methodological diversity, and frontier-method adoption lag. Results show that technical support is concentrated in scalable, content-ori
arXiv:2608.06831v1 Announce Type: new Abstract: The harms in which AI is implicated range in nature and scope from unsafe user interactions through to the societal-wide consequences of AI adoption. Classification of the diverse risks of AI is foundational to AI governance: regulators, technology firms, and policymakers need structured accounts of risk upon which to act. Researchers and practitioners have accordingly developed many Sociotechnical Outcome Taxonomies (SOT). This paper presents an empirical study of SOT development and use, drawing on 25 interviews with researchers and practitioners across industry, academia, civil society, and government. We find SOT are weakly integrated into AI governance processes, and identify two features of SOT design and use that explain why. First, the design choices through which SOT produce structured representations of the complex problem space of AI risks tend to be invisible to downstream taxonomy users. Those users treat the resulting catego
arXiv:2608.06782v1 Announce Type: new Abstract: Prior research has established the importance of student instructor preferences and identified various influencing factors. However, the dynamics of how student instructor preferences develop and change are less well understood, due to the limitations of common course structures and reliance on one-time measurements. To bridge this gap, we utilize data from a novel learning platform that provides students with access to instructional content created by multiple instructors. This platform enables the quantification of preference emergence and evolution throughout an entire semester, as students repeatedly select content from different instructors. Examining both initial and final student instructor preferences suggests that preference is a dynamic construct continually shaped by experiences. Furthermore, our analysis of the associations between preferences and student characteristics reveals a nuanced picture: while student attributes did
arXiv:2608.06753v1 Announce Type: new Abstract: Office hour utilization in computer science courses can spike near deadlines, producing long wait times, frustrated students, and overworked staff. To address this problem, a large CS1 course implemented a split deadlines policy. Students were randomly divided into two groups with staggered release and due dates. Each group had the same amount of time to complete assignments, but the number of students with each due date was reduced by half. Our study evaluates the effectiveness of this policy. We measure office hour utilization and staff efficiency near deadlines, examine the policy's impact on student performance, and investigate student perception of the policy's fairness and effectiveness. Overall we found that the split deadline policy increased office hour efficiency, resulted in no significant difference in performance between groups, and was considered fair and effective by most students. Our experience report includes reflections
arXiv:2608.06572v1 Announce Type: new Abstract: Students learning to program benefit from access to large numbers of practice problems. Autograders are commonly used to support programming questions by providing quick feedback on submissions. But authoring accurate autograders remains challenging. Autograders are frequently created by enumerating test cases--a tedious process that can produce inaccurate autograders that fail to correctly classify submissions. When authoring accurate autograders is slow, it is difficult to create large banks of practice problems to support beginning programmers. We present solution-generated autograding: a faster, more accurate, and more enjoyable way to create autograders. Our approach leverages a key difference between software testing and autograding: The question author can provide a solution. By starting with a solution, we can eliminate the need to manually enumerate test cases, validate the autograder's accuracy, and evaluate other aspects of sub
arXiv:2608.06510v1 Announce Type: new Abstract: Agentic AI promises a more flexible form of digital agency: systems that can act on users' behalf, from filtering content to negotiating prices to selecting services. Whether it will empower users is an open question, and we argue that the answer depends on more than the technology. We conduct a comparative case analysis of four more mature domains where similar forms of agency arose: browser-based ad blockers, platform recommender systems, financial robo-advisors, and email spam governance. Across the cases, decisions about whose interests agents would serve were resolved through technical arrangements: API choices, protocol governance, industry standards, and default configurations. Beyond their technical form, these were political decisions. We identify this as depoliticization, a concept from political theory, here at work in technological systems. Its most consequential effect is that individual outcomes and collective contestation c
arXiv:2608.06472v1 Announce Type: new Abstract: Unmanned Aerial Vehicles are now widely used across business, government, and recreational contexts, creating new challenges for incident response and digital forensics. While previous forensics research has largely focused on the extraction of technical data from UAV systems, minimal empirical work has examined how UAV incidents are handled in real-world settings or what challenges incident handlers face during this response. To address this gap, this paper reports findings from an in-person focus group with UAV and counter-UAV practitioners from industry and government organizations in the United States. Using qualitative analysis, several key challenges are identified, including situational awareness and airspace visibility, fragmented reporting and interorganizational coordination, forensic and attribution limitations, legal and policy gaps, and shortfalls in training and operational capacity. The research extends socio-technical inci
AI plagiarism is becoming more and more common in and outside of the classroom.
Higher education is rapidly developing AI governance frameworks through the creation/modification of policies, establishing compliance structures, conducting procurement reviews, and developing acceptable use guidelines. The post Beyond compliance: Governing higher education in the age of intelligent systems appeared first on eCampus News .
Early intervention based on accurate diagnosis of both metabolic risk factors and acute cardiac events could help make the difference between life and death for women. The post Advancing Women’s Heart Health Through Prevention and Rapid Diagnosis appeared first on MedCity News .
GSK gained rights to a Hutchmed antibody-targeted therapy conjugate, or ATTC. This new type of targeted therapy blocks two cancer-driving proteins and will initially be developed for lung, colorectal, and pancreatic cancers. The post GSK Pays $110M for Phase 1-Ready Hutchmed Asset in a New Class of Cancer Drugs appeared first on MedCity News .
Public confidence in higher education sits at a new historic low, and colleges and universities are facing an identity crisis. On the one hand, a growing chorus of reformers argues that colleges should reorganize themselves entirely around preparing students for the labor market, perhaps with good reason. The post The false choice between citizenship and a first job appeared first on eCampus News .
arXiv:2608.31082v2 Announce Type: replace-cross Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM agents that reason over this data to answer complex questions for every knowledge worker. Agents can do this today, but at prohibitive cost. Each question repeatedly opens large documents to recover scattered evidence, consuming up to a million tokens. However, if the data were already structured, the same question would reduce to a cheap database lookup. For example, on FanOutQA benchmark, reasoning over an ideal pre-structured store is 28X cheaper, and the gap grows to orders of magnitude as questions fan out over more documents. Yet structuring everything in advance is not viable: documents hold vastly more possible structure than any workload will use, and the useful structure and documents are unknown until queries arrive. We propose agentic data cracking, a
arXiv:2605.29068v2 Announce Type: replace-cross Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning. Reasoning-based guardrails significantly outperform classification-only baselines, but they incur substantial query latency and token overhead that make them impractical for highthroughput deployment. To address this challenge, we propose COLAGUARD, a guardrail model that transfers multi-step safety reasoning into a continuous latent space through a stage-wise training curriculum, enabling direct hidden-state propagation at inference. Evaluated on ten prompt- and response-moderation settings spanning eight safety benchmarks, COLAGUARD improves macro-F1 by 8.24 points over Llama Guard 3 and matches our explicit reasoning baseline, GuardReasoner, in macroF1 while delivering a 12.9X speedup and 2
arXiv:2605.02720v2 Announce Type: replace-cross Abstract: Vision-language models hold considerable promise for ophthalmology, but it remains unclear which training data source best conveys expert domain knowledge. Existing ophthalmic models are trained on fixed text templates, medical reports, or general biomedical literature, sources that have never been compared under matched conditions. To include domain-specific literature in this comparison, we present PubMed-Ophtha, a hierarchical dataset with high domain density of 102,023 panels with their subcaptions from 15,842 open-access articles in PubMed Central. We then finetuned identical CLIP models on each source, using a general biomedical literature model as baseline, and found that domain-specific literature achieved the best average performance across 110 clinical tasks, reaching a mean linear probing AUROC of 88.63% ahead of medical reports (85.68%). Restricting the dataset to fundus images, to the image count of the medical repo
arXiv:2603.23037v2 Announce Type: replace-cross Abstract: The trustworthy object detection capabilities of a novel Kolmogorov-Arnold network framework are examined here. The approach addresses a key limitation in computer vision for vehicle detection perception, and beyond. These systems offer limited transparency regarding the reliability of their confidence scores in visually degraded or ambiguous scenes. To this end, a Kolmogorov-Arnold network is employed as an interpretable post-hoc surrogate to model the trustworthiness of the You Only Look Once (Yolov10) detections using seven geometric and semantic features. The additive spline-based structure of the Kolmogorov-Arnold network enables direct visualisation of each feature's influence. This produces smooth and transparent functional mappings that reveal when the model's confidence is well supported and when it is unreliable. Furthermore, a bootstrapped language-image (BLIP) foundation model generates descriptive captions of each s
arXiv:2606.23989v4 Announce Type: replace Abstract: Large language models produce fluent multi-document summaries, but their attributions are typically coarse---whole documents or passages---and generated post hoc, leaving each statement hard to verify. We argue that attribution should be a structural property of generation rather than a downstream prediction. We present CAMS, a Claim-Anchored Multi-document Summarization framework that decomposes every source document into atomic claims whose provenance is resolved deterministically from verbatim quotes to token spans, clusters equivalent claims across documents while flagging inter-source conflicts, selects a support-aware and salient subset, and rewrites it so that every summary sentence terminates in claim identifiers resolving back to source spans. This yields a separation we make explicit: provenance is an invariant holding for every emitted sentence independently of model accuracy, whereas faithfulness is an objective that selec
arXiv:2606.19667v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding, but it also lengthens prompts and raises prefill cost. Prefix caching in serving engines such as vLLM reduces this cost only when requests share the same token prefix. In grounded generation, however, adjacent queries may retrieve overlapping evidence in different orders, so set overlap does not become reusable prefix overlap. We present CacheWeaver, a lightweight prompt-layer method for cache-aware evidence ordering. The method keeps a prefix tree over recently served evidence sequences and uses a greedy walk to place the most reusable prefix first, while leaving the serving engine and retrieved evidence set unchanged. Across three vLLM configurations, the method lowers median time-to-first-token (TTFT) by about 20-33 percent relative to retrieval-order prefix caching, without hurting answer quality in our QA tests. The greedy policy reaches 97.5 percent of the median T
arXiv:2606.12807v2 Announce Type: replace Abstract: Summaries of real-world events can become outdated as contexts evolve and new information arrives. A common response is to generate a new summary from the updated context, but full regeneration discards the previous draft, can obscure what changed, and may be unnecessary when only a few claims are unsupported. We study localized faithfulness repair: updating outdated spans in an existing summary while preserving supported content. We propose DETECT-REMASK-REPAIR, a diffusion-based framework that identifies, remasks, and repairs outdated regions with masked diffusion language models. To evaluate evolving-context summarization, we introduce StreamSum, a benchmark of synthetic event timelines. Experiments on DialogSum and StreamSum show that localized diffusion repair provides a controllable alternative to full rewriting: faithfulness-steered repair improves early drafts, one-step repair reduces repair cost to under half a second, with t
arXiv:2606.10403v3 Announce Type: replace Abstract: Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together they expose, across a wide range of VLMs (and LLMs with OCR), three patterns: (i) low-budget accuracy collapses on the high-human-error tail at every model size; (ii) test-time scaling (TTS) raises token use roughly linearly with cohort error rate, while accuracy gains follow a non-monotonic curve; (iii) within a single family, TTS flips between ant
arXiv:2606.07537v2 Announce Type: replace Abstract: Large language models produce fluent, confident, factually wrong output. Existing taxonomies classify these failures by output type -- intrinsic versus extrinsic, faithfulness versus factuality -- but say nothing about which computational component produced a given failure. We ask what would be required to attribute an individual hallucination to a specific component of the decoder-only stack. We treat three components -- self-attention's associative retrieval, the maximum-likelihood pretraining objective, and autoregressive commitment under exposure bias -- as candidate failure surfaces, justify their separability rather than assuming it, and specify an attribution procedure requiring only sampling access: an ordered set of three interventions on prefix, context, and frequency competition, together with a validation design based on independent annotation and a classifier baseline. We state five falsifiable predictions and identify co
arXiv:2605.25731v3 Announce Type: replace Abstract: Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we use enhanced prompts throughout training by incorporating original prompt texts and trait descriptions, providing richer semantic information for trait-specific score generation. Experiments across multiple backbone models show that our method consistently improves multi-trait scoring performance over supervised fine-tuning and scalar-reward optimization baselines, demonstrating the effective
arXiv:2605.15913v5 Announce Type: replace Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic segmentation dataset containing over 30k instances across 16 categories-including books, code, web text, and conversations with text lengths ranging from 2k to 32k. Using this dataset, we train a lightweight segmenter to automatically partition text into human-instinct-aligned blocks with controllable granularity. Second, we propose block distillation, a training framework that is more efficient than b
arXiv:2604.07035v3 Announce Type: replace Abstract: Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection difficult to interpret. We present a unified evaluation of seven open reasoning language model configurations across four benchmarks: ARC-Challenge, GSM8K, MATH levels 1 to 3, and TruthfulQA MC1. We test zero-shot, chain-of-thought (CoT), and few-shot CoT prompting on the same 238-example subset for every model--dataset--strategy condition, yielding a complete 7 x 4 x 3 design with 84 conditions and 19,992 evaluated examples. Beyond accuracy, we report Wilson confidence intervals, latency, peak video random access memory (VRAM), weighted aggregate performance, Pareto-efficient operating points, prompt-sensitivity metrics, and compatibility diagnostics. Gemma-4-26B-A4B with zero-shot prompting achieves the highest weighted score at 0.794. Gemma-4-E4B remains c
arXiv:2603.25183v2 Announce Type: replace Abstract: Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextual signals are unevenly beneficial across sentences. Existing training objectives do not explicitly model this variability, limiting a model's ability to adaptively exploit context. In this paper, we propose Cross-Preference Learning (CPL), a preference-based training framework that explicitly captures the complementary benefits of sentence-level and context-aware MT. CPL achieves this by integrating both intra- and cross-condition preferences into the preference optimization objective, providing explicit supervision to exploit informative context while remaining robust to uninformative context. We validate the proposed approach on several public context-aware MT tasks using multiple models, including Qwen3-4B, Qwen3-8B, and Llama-3-8B-Instruct. Experimental results demonstrate consistent i
arXiv:2603.21438v3 Announce Type: replace Abstract: To discover the weaknesses of LLMs, researchers often embed prompts into a vector space and cluster them to extract insightful patterns. However, vector embeddings primarily capture topical similarity; as a result, prompts that share a topic but differ in specificity, and consequently in difficulty, are often represented similarly, making fine-grained weakness analysis difficult. To address this limitation, we propose Prompt2Box, which embeds prompts into a box embedding space using a trained encoder. The encoder, trained on existing and synthesized datasets, outputs box embeddings that capture not only semantic similarity but also specificity relations between prompts (e.g., "writing an adventure story" is more specific than "writing a story"). We further develop a novel dimension reduction technique for box embeddings to facilitate dataset visualization and comparison. Our experiments demonstrate that box embeddings consistently cap
arXiv:2603.05617v2 Announce Type: replace Abstract: We present NotAI.AI, an explainable AI-generated text detection system. Instead of returning only a binary label or confidence score, the system shows which signals influenced the prediction and lets users inspect an attribution-based sensitivity estimate obtained by subtracting selected local contributions. NotAI.AI combines sentence-level conditional probability curvature, a neural detector score, and interpretable stylometric and readability features in an XGBoost meta-classifier. It explains predictions with TreeSHAP feature contributions and can turn the resulting evidence into a concise natural-language explanation. We evaluate the system on a category-balanced subset of RAID containing human-written, clean AI-generated, and attacked AI-generated texts. The full model outperforms variants based on individual feature families, reaching 0.9685 F1 on the held-out within-subset test split. In an automatic evaluation, two model judge
arXiv:2601.04202v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards encode much of their technical information in complex tables, but LLM knowledge and interpretation of such tables remain largely unexplored. We introduce TeleTables, a benchmark comprising 2,220 tables from 13 3GPP specifications in four formats and 500 human-verified MCQs spanning direct retrieval to multi-step reasoning. Evaluating 20 open-weight LLMs across non reasoning, multimodal, reasoning, and table specialized architectures reveals two distinct performance bottlenecks. In the closed-book setting, domain knowledge is the primary constraint, with no general-purpose model exceeding 41% accuracy. When the table is provided as context, the best models exceed 90%, but performance degrades systematically with reasoning depth, evidence scope, and structural complexity, with a 32.2pp spread acr
arXiv:2509.22480v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this paper, we study a new perspective: the divergence in solutions generated by LLMs for a single problem. We show that higher solution divergence is positively related to better problem-solving abilities across various models. Based on this finding, we propose solution divergence as a novel metric that can support both SFT and RL strategies. We test this idea on three representative problem domains and find that using solution divergence consistently improves success rates. These results suggest that solution divergence is a simple but effective tool for advancing LLM training and evaluation.
arXiv:2509.21889v3 Announce Type: replace Abstract: Existing evaluations of foundation models predominantly focus on output correctness, treating interaction as a static exchange of information. However, such perspectives overlook the essence of the LLM-driven conversational experience, which is determined not only by content quality but, crucially, by dynamic service attributes such as generation velocity and latency patterns. To address this gap, we introduce QoNext, the first framework that adapts Quality of Experience (QoE) principles from networking and multimedia to the holistic assessment of human-AI interaction. QoNext identifies experiential factors that shape user experience and incorporates them into controlled experiments in simulated interaction scenarios, where human ratings are collected under diverse configurations. From these studies we construct the QoNext Database and train the QoNext Model, a neural predictor that estimates user experience directly from measurable s
arXiv:2506.07309v3 Announce Type: replace Abstract: Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation costs? In this work, we address both challenges simultaneously. We introduce ConfQA, a fine-tuning strategy that reduces hallucination rates from 20-40% to below 5% across multiple factuality benchmarks. The approach is simple: when the model answers correctly, it is trained to output the answer; otherwise, it is trained to respond with "I am unsure". Two design choices make this training effective: (1) a dampening prompt ("answer only if you are confident") that explicitly discourages overconfident hallucinations, and (2) training data drawn from atomic factual statements (e.g., knowledge graph attribute values), which calibrates model confidence and yields robust generalization across domains and question types. Building on ConfQA, we
arXiv:2503.24377v2 Announce Type: replace Abstract: Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutio
arXiv:2408.06737v2 Announce Type: replace Abstract: This work presents an extensive study of transformer-based NLP models application for detection of social media posts that contain verifiable factual claims and harmful claims. The study covers various activities, including dataset collection, dataset pre-processing, architecture selection, setup of settings, model training (fine-tuning), model testing, and implementation. The study includes a comprehensive analysis of different models, with a special focus on multilingual models where the same model is capable of processing social media posts in both English and in low-resource languages such as Arabic, Bulgarian, Dutch, Polish, Czech, Slovak. The results obtained from the study were validated against state-of-the-art models, and the comparison demonstrated the robustness of the proposed models. The novelty of this work lies in the development of multi-label multilingual classification models that can simultaneously detect harmful po
arXiv:2609.05401v1 Announce Type: cross Abstract: Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same reward under semantically equivalent goal descriptions. We show that current VLM reward models often violate this property. Paraphrasing the instruction alone can substantially change predicted progress scores, and can even flip identical robot behavior between failure and success. To measure this failure mode, we introduce ROBORMBENCH, a benchmark with 2,390 real-robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites. Across proprietary and open-source VLMs, paraphrase-induced instability is widespread and severe, grows under more divergent rewrites, and is not reliably reduced by scale or explicit reasoning. Dedicated reward models trained with trajectory-grounded supervision are s
arXiv:2609.05395v1 Announce Type: cross Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source models consistently underperform in this multi-step setting, and no existing benchmark measures the gap. We introduce the Korean Open Public API Benchmark (KOPA-Bench), comprising 145 real-world tasks. To close this gap, we present EDGE, an Execution-grounded Dynamic Graph for tool-calling data synthEsis driven by live execution. EDGE builds a graph of how each tool's output can feed another's input, keeps only the links that succeed when actually called against the live APIs, and traverses these verified links to synthesize executable multi-step trajectories. Fine-tuned via GRPO on the resulting dataset, our 9B model nearly matches the untuned 27B model from the same family, improving substantially not only on KOPA-Bench but also on the BFCL b
arXiv:2609.05339v1 Announce Type: cross Abstract: Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only $+0.0004 \pm 0.0020$ following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by $+9.91$ or $-13.
arXiv:2609.05333v1 Announce Type: cross Abstract: A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate that word's occurrences by context in its later layers. Testing this belief cleanly requires a construct that holds the word form fixed while its context and intended sense vary in a controlled, labeled way. This manual documents an open toolkit built around such a construct, which we call a bridge form: a single written word that recurs, unchanged, across two or more subject domains with a different sense in each. We describe, and justify, every stage of the pipeline: the declarative specification of bridge forms and their source domains, corpus acquisition from Wikipedia, occurrence localization, layer-wise representation extraction, a domain-pairwise silhouette measurement of separation in the model's representation space, and a paired visualization protocol. Each design choice is pres