ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “evaluations”

15 stories in the last 24h

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI safety & security 16AI research 15Industry 8AI industry 8Research 5Advisory 4Vulnerability 3AI policy 2Data breach 1Malware 1Exploit / PoC 1Threat actor 1Tools 1AI tools & infra 1
SeverityAllcritical 0high 4medium 3low 4info 56

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

Researchers prove off-policy evaluation under history-dependent logging requires exponentially many episodes, resolving a hardness question for model-based POMDP evaluation.

The paper constructs POMDPs with at most two latent states per stage, three actions, and a three-memory-state logger where evaluating a known deterministic target policy to accuracy 1/8 requires Θ((3/2)^H log(1/δ)) episodes for any horizon H≥3. Coverage and outcome-revealing conditions hold with constants independent of H, yet a reset erases the unknown transition that determines the target value. The authors characterize the resulting statistical experiment exactly, derive a matching optimal estimator, and validate predictions on a two-lane gridworld. This settles the history-dependent-logging, model-based case posed by Zhang and Jiang (arXiv:2503.01134).

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation

Study shows radiology reporting-style variations in reference reports can flip rankings of chest X-ray report generation models; releases MIMIC-CXR-Ext-ReRef dataset.

The paper quantifies how variations in radiologists' reporting practices distort evaluation of radiology report generation (RRG) models, introducing a radiologist-informed taxonomy and the ReRef method for rewriting reference reports while preserving clinical meaning. On MIMIC-CXR with RadCliQ-v1, condensing normal-findings discussion caused Libra to drop from first to second while CheXOne rose from third to first among nine models. The authors release MIMIC-CXR-Ext-ReRef, a radiologist-validated dataset of 120 original/alternative reference pairs, arguing metrics conflate clinical correctness with stylistic conformity.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria

Survey of 761 Nigerian healthcare professionals finds high AI awareness (92.6%) but limited knowledge, preparedness, and major training and infrastructure barriers.

A cross-sectional study of 761 healthcare professionals across Nigeria, conducted from December 2025 to March 2026, found 92.6% awareness of AI in healthcare but 40.9% reporting low knowledge and only 63.0% feeling adequately prepared. Top barriers were lack of training (84.7%), poor infrastructure (71.1%), and high tool costs (61.0%). Willingness to adopt was strong, with 92.5% interested in training and 78.7% supporting AI in undergraduate curricula; preparedness differed significantly across geopolitical zones and professions.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education

Introduces MUSE, a twelve-task benchmark evaluating vision-language models on artistic image understanding in situated educational, Southeast Asian contexts.

MUSE is a benchmark assessing large vision-language models on artistic image understanding across twelve tasks spanning visual perception, semantic and affective interpretation, cultural understanding, and compositional reasoning. It decouples image annotation from question generation for controllable difficulty and curates images centering Singaporean and Southeast Asian multicultural contexts alongside Western art. Evaluations of open-source and proprietary models found substantial disparities, especially in affective interpretation and compositional reasoning.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Objective vs. Search: Decomposing What Makes a Good Tokeniser

New tokeniser study shows search procedure, not optimisation objective, drives bits-per-byte performance across model sizes, vocabulary sizes, and multilingual settings.

The paper disentangles BPE and UnigramLM along two axes: optimisation objective (compression vs log-likelihood) and search procedure (bottom-up merging vs top-down pruning). Two new algorithms, BottomUpLL and TopDownComp, complete the 2x2 design space, and trained language models are evaluated on bits-per-byte and BLiMP across model sizes, vocabulary sizes, and English-only vs multilingual domains. Bottom-up tokenisers consistently achieve lower bits-per-byte in most settings, while BLiMP shows no consistent relationship with design choice.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

PANORAMA grounds vision-language caption phrases in pixel-level masks via mask proposal selection, achieving state-of-the-art grounding on the new PanoCaps benchmark.

The paper introduces panoptic grounded captioning, requiring VLMs to describe foreground and background regions while grounding each phrase with pixel-level masks. Contributions include PanoCaps, a human-annotated benchmark built from panoptic segmentation datasets with entity-level image-text alignment, a phrase-mask matching protocol, and a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations to select masks, achieving the best overall grounding on PanoCaps; code, data, and models are released.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research 2 sources

Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking

DualViewEval compresses agent benchmarks by jointly modeling outcome and process signals, achieving 24x-40x compression with only 20 tasks on APEX-Agents and BFCL.

DualViewEval is an agent benchmark compression method that jointly exploits outcome and process relations from trajectories to learn exact-size minisets predicting full-benchmark scores. The authors analyze large-scale trajectories and identify six process signals systematically associated with final agent performance. Across five agent benchmarks and five baselines, it achieves the best results on all datasets: with only 20 tasks it reaches 24x-40x compression on APEX-Agents and BFCL, reduces MAE by 14.5%-28.2% over the strongest competitors, and improves Kendall's tau by up to 7.2% relative to EssenceBench on SWE-bench Verified.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research1

Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation

Pipeline pairs generated video with audio-derived force profiles to enable zero-shot, force-aware robot manipulation on Franka Panda for contact-rich tasks.

The paper leverages generated video and audio jointly: loudness of generated contact sounds shapes a bounded, time-varying desired-force profile from a natural-language task prompt. Trajectories execute on a Franka Panda robot with a closed-loop force regulator tracking the audio-shaped profile, succeeding where a kinematic-only baseline fails. The pipeline also serves as a data generation engine to train closed-loop manipulation policies.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

ScienceIDE turns scientific code repositories into agent-trainable environments and trains PhAI-IDE models at 72B, 9B, and 4B scales.

ScienceIDE is infrastructure that transforms scientific repositories into executable environments supporting task generation, execution, and scientific verification, guided by expert-defined cases and acceptance criteria. Using verified interaction trajectories, the authors train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family improves held-out scientific-code repair and selected general benchmarks in code, reasoning, and knowledge, indicating positive transfer. Code is released on GitHub.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research 2 sources

Affora: A Design System for Agent-Friendly Interfaces

Affora is a design system making interfaces legible to computer-use agents while preserving human workflows, with reusable components and executable checks.

Affora supports both human users and computer-use agents through a shared interface rather than a separate agent-only surface. Three controlled studies cover component implementations, visual variation, and interaction-design principles, producing guidance from individual components to complete sites with reusable implementations and executable checks. Evaluation on independently authored interfaces shows gains where agent-readability deficits exist, limited effects where they do not, and a workflow case gives preliminary evidence of reduced interaction cost.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models

Six frontier models play a two-agent log(N)-Questions game; Claude Opus 5 lags with 28/68 wins while the top five are near-tied.

The study evaluates six frontier models on a two-agent game where a questioner must identify one of N Wikipedia lead paragraphs in exactly log2 N yes/no questions, run over 408 games at $363 total API cost. Claude Opus 5 wins 28 of 68 games versus 45-56 for GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash, and Kimi K3. Pooled top-five win rates decline with set size (r=-0.973) and fit win = p^(log2 N) with per-round reliability p=0.928, and information per question correlates with win rate at r=+0.88.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research 20 sources

Probabilistic Linear Explanations

Researchers introduce a unified probabilistic explainability framework using sparse anchored linear models that outperforms LIME and MAPLE on relevance error.

The paper proposes probabilistic explanations based on sparse, anchored linear models applicable to both binary classification and continuous regression. It proves that minimizing relevance error for neural-network models is NP-hard and relates it to a tractable fidelity-error surrogate. Solutions are computed via a mixed integer programming formulation with provably optimal empirical solutions and a polynomial-time iterative hard thresholding algorithm with approximation guarantees. Empirical evaluations show lower relevance error than LIME and MAPLE while satisfying anchoring and sparsity constraints by construction.

arXiv cs.AI / cs.LG / cs.CL · 19h agoAI research

Social Laws for Multi-agent Coordination in Stochastic Environments

Researchers extend social laws to stochastic, reward-based multi-agent environments, defining alpha-robustness and a verification method via Markov decision processes.

The paper extends the concept of social laws from deterministic, goal-based settings to stochastic, reward-based multi-agent environments. It introduces alpha-robustness, a measure of the guaranteed utility each agent retains while pursuing its optimal single-agent policy assuming all agents obey the social law. Robustness verification is reduced to solving a series of Markov decision processes, with empirical evaluations on toy environments.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards

ECtHR-NPD benchmark covers 14,575 European Court of Human Rights cases for predicting non-pecuniary damage awards; LLMs struggle with zero and high awards.

Researchers introduce ECtHR-NPD, described as the first benchmark for predicting non-pecuniary damage awards at the European Court of Human Rights from case information where no statutory formula exists. It contains 14,575 cases with case-level awards in nominal euros, chronological splits, and a protocol separating target construction from model input. Evaluations covering constant predictors, gradient-boosted trees, retrieval methods, fine-tuned encoder LMs, prompted decoder LMs, and knowledge-augmented agents show sophisticated LM approaches do not consistently outperform the strongest feature-based baseline. All model families struggle to identify zero awards and to calibrate high-award predictions, with further degradation on a Challenging test view.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

Structured Claim-Level Discourse Representations for Dense Health Narratives

Researchers propose a claim-level discourse framework for health videos, finding 13.22 atomic claims per minute and that LLMs struggle with pragmatic profiling.

The paper introduces a structured framework for claim-level discourse analysis in dense health narratives on social media videos, modeling tuples that link atomic claims with thematic aspects, stance, and multidimensional pragmatic attributes. Analysis found an average of 13.22 atomic claims per minute in health video discourse. A benchmark spanning four health domains with 1,191 manually annotated claims from 60 videos shows current LLMs perform strongly on thematic categorization and stance prediction but struggle with high-dimensional pragmatic profiling, suggesting future systems need task decomposition and specialized inference strategies.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research