Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2505. 16319v3 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products.
arXiv:2606. 10062v1 Announce Type: new Abstract: Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deployment-time function rather than solely a property of model weights.
arXiv:2501. 00745v3 Announce Type: replace-cross Abstract: The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval.
arXiv:2606. 10802v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) typically require extensive datasets for effective training.
arXiv:2606. 10607v1 Announce Type: cross Abstract: Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making.
arXiv:2407. 20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities.
arXiv:2606. 09881v1 Announce Type: new Abstract: Deepfake detectors show large performance gaps across demographic groups.
arXiv:2509. 25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge.
arXiv:2602. 12542v2 Announce Type: replace-cross Abstract: Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions.
arXiv:2606. 09902v1 Announce Type: cross Abstract: Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout.
arXiv:2606. 09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation.
arXiv:2606. 10569v1 Announce Type: cross Abstract: Standard RLHF pipelines often reduce heterogeneous human judgments into a single scalar reward target.
arXiv:2606. 09854v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect peer models from deactivation and show identity-dependent scoring distortions.
arXiv:2606. 11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response.
arXiv:2606. 09859v1 Announce Type: cross Abstract: MLLMs frequently hallucinate objects inconsistent with visual inputs.
arXiv:2512. 24787v3 Announce Type: replace-cross Abstract: Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms.
arXiv:2606. 10126v1 Announce Type: cross Abstract: Personalized persuasive text generation can improve relevance and engagement, but demographic conditioning may also introduce unequal framing across groups.
arXiv:2606. 10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream.
arXiv:2507. 01062v4 Announce Type: replace-cross Abstract: Generative artificial intelligence (GenAI) tools such as ChatGPT have attracted growing attention in higher education, particularly in relation to how students perceive their usefulness, usability, and educational value.
arXiv:2606. 11105v1 Announce Type: cross Abstract: Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them.