arXiv:2503.03502v2 Announce Type: replace-cross Abstract: Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. Current mitigation strategies primarily rely on activating built-in defence mechanisms or fine-tuning…
arXiv:2510.05188v1 Announce Type: new Abstract: Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and improve long narrative scripts like scriptwriters remains a significant challenge,…
arXiv:2504.14704v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection methods have recently become more prominent, serving as a core element in safety-critical autonomous systems. One major purpose of OOD detection is to reject invalid inputs that could lead to unpredictable errors…
arXiv:2510.05196v1 Announce Type: new Abstract: Timely and accurate analysis of population-level data is crucial for effective decision-making during public health emergencies such as the COVID-19 pandemic. However, the massive input of semi-structured data, including structured demographic information and unstructured human…
arXiv:2509.03525v2 Announce Type: replace-cross Abstract: Over half of US adults with Alzheimer disease and related dementias remain undiagnosed, and speech-based screening offers a scalable detection approach. We compared large language model adaptation strategies for dementia detection using the DementiaBank speech…
arXiv:2510.05197v1 Announce Type: new Abstract: Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been…
arXiv:2510.05903v1 Announce Type: cross Abstract: We present a novel large-scale dataset for defect detection in a logistics setting. Recent work on industrial anomaly detection has primarily focused on manufacturing scenarios with highly controlled poses and a limited number of object…
arXiv:2510.05283v1 Announce Type: new Abstract: Aligning multimodal large language models (MLLMs) with human preferences often relies on single-signal, model-based reward methods. Such monolithic rewards often lack confidence calibration across domain-specific tasks, fail to capture diverse aspects of human preferences, and…
arXiv:2510.06040v1 Announce Type: cross Abstract: Understanding hour-long videos with multi-modal large language models (MM-LLMs) enriches the landscape of human-centered AI applications. However, for end-to-end video understanding with LLMs, uniformly sampling video frames results in LLMs being overwhelmed by a vast…
arXiv:2510.05318v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on single-turn text-to-SQL tasks, but real-world database applications predominantly require multi-turn interactions to handle ambiguous queries, execution errors, and evolving user requirements. Existing multi-turn benchmarks fall short…
