Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot.
arXiv:2608. 10171v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption.
arXiv:2608. 10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty.
arXiv:2606. 07271v3 Announce Type: replace-cross Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy.
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. 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: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. 10433v1 Announce Type: new Abstract: Forecast accuracy does not tell us which past inputs produced a prediction.
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:2509. 05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior?
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: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:2508. 13831v4 Announce Type: replace-cross Abstract: Functional data, i.
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: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: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:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
arXiv:2310. 15976v4 Announce Type: replace Abstract: signSGD is attractive in nonconvex optimization because it communicates sign-valued rather than full-precision gradients.
arXiv:2608. 10530v1 Announce Type: cross Abstract: Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory.