Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 27995v2 Announce Type: replace-cross Abstract: Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency.
arXiv:2608. 12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods.
arXiv:2608. 13039v1 Announce Type: new Abstract: The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks.
arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.
arXiv:2608. 12355v1 Announce Type: cross Abstract: Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebases to executing long-horizon development workflows.
arXiv:2608. 12779v1 Announce Type: cross Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment.
arXiv:2608. 13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally?
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. 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:2604. 17299v3 Announce Type: replace-cross Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones.
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. 13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims.
arXiv:2608. 12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with conservative defaulting.
arXiv:2608. 13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading).
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. 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. 12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases.
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.