Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making.
arXiv:2608. 11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions.
arXiv:2605. 17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages.
arXiv:2509. 05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior?
arXiv:2608. 00144v2 Announce Type: replace Abstract: Membership inference (MIA) on language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate members from non-members using surface text alone.
arXiv:2508. 13831v4 Announce Type: replace-cross Abstract: Functional data, i.
arXiv:2512. 06227v3 Announce Type: replace-cross Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky behaviours for online safety, yet labelling such information is often costly and/or difficult due to its multi-label and dynamic nature.
arXiv:2608. 10384v1 Announce Type: new Abstract: This paper studies inverse sampling for L\'evy-driven generative models from the perspective of Markov generators.
arXiv:2508. 07617v2 Announce Type: replace-cross Abstract: AI has the potential to augment human decision making.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv:2608. 10433v1 Announce Type: new Abstract: Forecast accuracy does not tell us which past inputs produced a prediction.
arXiv:2602. 01747v2 Announce Type: replace-cross Abstract: Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools.
arXiv:2601. 22012v3 Announce Type: replace Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms.
arXiv:2505. 22839v2 Announce Type: replace-cross Abstract: Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models.
arXiv:2608. 10405v1 Announce Type: cross Abstract: Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead and resource consumption.
arXiv:2608. 09992v1 Announce Type: cross Abstract: Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of samples with explicit constraints on semantic content, structural properties, and variability.
arXiv:2603. 29418v2 Announce Type: replace-cross Abstract: Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks.
arXiv:2608. 10206v1 Announce Type: new Abstract: Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech.
arXiv:2504. 11500v3 Announce Type: replace-cross Abstract: Transit Origin-Destination (OD) data are fundamental for optimizing public transit services, yet current collection methods, such as manual surveys, Bluetooth/WiFi tracking, and Automated Passenger Counters, are often costly, device-dependent, or unable to support individual-level matching.
arXiv:2608. 11006v1 Announce Type: cross Abstract: Governments worldwide have responded to the rapid expansion of AI by publishing national and regional AI strategies.