Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.
arXiv:2608. 13461v1 Announce Type: new Abstract: Post-click conversion rate (CVR) is a key metric in various scenarios including e-commerce and advertising, reflecting the efficiency and user experience in the second stage of the conversion process.
arXiv:2608. 12408v1 Announce Type: cross Abstract: Representational similarity analysis (RSA) is increasingly used to ask which learning rules give convolutional networks brain-like representations.
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
arXiv:2608. 13221v1 Announce Type: new Abstract: The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and allocate reasoning resources--that is, how they organize search.
arXiv:2608. 12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcement learning, and an in-depth understanding of reasoning behaviors during model performance evaluation.
arXiv:2608. 12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging.
arXiv:2608. 12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models.
arXiv:2608. 12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers.
arXiv:2608. 12805v1 Announce Type: new Abstract: Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification.
arXiv:2412. 17228v4 Announce Type: replace Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials.
arXiv:2608. 12874v1 Announce Type: new Abstract: Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks.
arXiv:2608. 13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels.
arXiv:2608. 12477v1 Announce Type: new Abstract: Clinical prediction models are often developed as if the outcome of interest were cleanly observed for every patient.
arXiv:2508. 14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical applications.
arXiv:2608. 13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally?
arXiv:2608. 12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates.
arXiv:2608. 12564v1 Announce Type: new Abstract: Automating empirical research is a long-standing direction of AI.
arXiv:2608. 13467v1 Announce Type: new Abstract: We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ \pi(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is convex and \(G\)-Lipschitz.