Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2406. 11868v2 Announce Type: replace-cross Abstract: The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection, diagnosis, and treatment planning.
arXiv:2608. 07523v1 Announce Type: cross Abstract: Difficulty differences across parallel-class programming examinations affect the fairness of course assessment.
arXiv:2511. 10453v4 Announce Type: replace-cross Abstract: Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong.
arXiv:2608. 08180v1 Announce Type: cross Abstract: Abstractive text summarization systems frequently generate fluent yet unfaithful summaries by fabricating or distorting relationships between entities and events.
arXiv:2605. 12991v3 Announce Type: replace-cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy.
arXiv:2608. 07534v1 Announce Type: cross Abstract: Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival.
arXiv:2608. 08024v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations.
arXiv:2608. 07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs).
arXiv:2608. 09653v1 Announce Type: cross Abstract: Recent advances in learning-based control have enabled impressive achievements in solving complex control problems in various domains.
arXiv:2608. 09314v1 Announce Type: new Abstract: In a federated learning setup for GANs, several adversarial attacks are possible.
arXiv:2608. 08430v1 Announce Type: cross Abstract: Virtual cells employ machine learning models to simulate and predict cellular behaviors, serving as a critical computational framework for investigating health and disease.
arXiv:2608. 09688v1 Announce Type: cross Abstract: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias.
arXiv:2608. 09622v1 Announce Type: new Abstract: Reliability qualification of advanced semiconductor devices requires sequential stress decisions that balance characterization objectives against multiple competing failure mechanisms.
arXiv:2608. 08883v1 Announce Type: new Abstract: Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows.
arXiv:2608. 09580v1 Announce Type: new Abstract: Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user interests across related domains.
arXiv:2608. 09332v1 Announce Type: new Abstract: Hallucinations are a major concern for the integration of artificial intelligence into medicine, although less explored in the realm of medical image processing.
arXiv:2608. 09523v1 Announce Type: new Abstract: Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimization theory does not fully explain this success.
arXiv:2608. 07978v1 Announce Type: cross Abstract: Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical tasks.
arXiv:2608. 07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers.
arXiv:2608. 07822v1 Announce Type: cross Abstract: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood.