arXiv:2604.01924v1 Announce Type: new
Abstract: Accurate short-term mortality prediction in heart failure (HF) remains challenging, particularly when relying on structured electronic health record (EHR) data alone. We evaluate transformer-based models…
arXiv:2604.01925v1 Announce Type: new
Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks …
arXiv:2604.01936v1 Announce Type: new
Abstract: Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant appro…
arXiv:2604.02207v1 Announce Type: cross
Abstract: Background: Accurate translation of radiology reports is important for multilingual research, clinical communication, and radiology education, but the validity of LLM-based evaluation remains unclear. …
arXiv:2604.02028v1 Announce Type: new
Abstract: Diffusion models have become a standard approach for generative modeling in continuous domains, yet their application to discrete data remains challenging. We investigate why Gaussian diffusion models wi…
arXiv:2407.15828v2 Announce Type: replace
Abstract: Spoken dialogue is essential for human-AI interactions, providing expressive capabilities beyond text. Developing effective spoken dialogue systems (SDSs) requires large-scale, high-quality, and dive…
arXiv:2604.02043v1 Announce Type: new
Abstract: Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model tr…
arXiv:2604.02045v1 Announce Type: new
Abstract: Transforming causal generative language models into bidirectional encoders offers a powerful alternative to BERT-style architectures. However, current approaches remain limited: they lack consensus on op…
arXiv:2604.02135v1 Announce Type: new
Abstract: Multilingual large language models (LLMs) often exhibit emergent ‘shadow’ capabilities in languages without official support, yet their performance on these languages remains uneven and under-measured. T…
arXiv:2410.17954v2 Announce Type: replace-cross
Abstract: Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modul…