arXiv:2603.24125v1 Announce Type: new
Abstract: During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typic…
arXiv:2602.11391v2 Announce Type: replace
Abstract: Objective: This paper introduces a patient simulator for scalable, automated evaluation of healthcare conversational agents, generating realistic, controllable interactions that systematically vary a…
arXiv:2603.24500v1 Announce Type: new
Abstract: Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty-based methods offer soft regularization, t…
arXiv:2603.20581v2 Announce Type: replace
Abstract: Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social …
arXiv:2603.21494v2 Announce Type: replace
Abstract: The Brain Tumor Reporting and Data System (BT-RADS) standardizes post-treatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication…
arXiv:2603.24307v1 Announce Type: new
Abstract: We release Samas\=amayik, a novel, meticulously curated, large-scale Hindi-Sanskrit corpus, comprising 92,196 parallel sentences. Unlike most data available in Sanskrit, which focuses on classical era te…
arXiv:2603.24413v1 Announce Type: new
Abstract: Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, every line of a verse is typically a fixed length sequence…
arXiv:2603.23688v1 Announce Type: cross
Abstract: Background: Determining an adequate sample size is essential for developing reliable and generalisable clinical prediction models, yet practical guidance on selecting appropriate methods remains limite…
arXiv:2603.23961v1 Announce Type: new
Abstract: Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and mo…
arXiv:2603.24580v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in domains characterize…