Generative artificial intelligence (AI) has rapidly become embedded in academic writing, assisting with tasks ranging from language editing to drafting text and producing evidence. Despite

Background: Generative artificial intelligence (GenAI) tools are increasingly used in scientific research to support literature searches, evidence synthesis, and manuscript preparation. While these systems promise

Background: The integration of artificial intelligence–generated content (AIGC) tools into academic research offers transformative potential for enhancing productivity and innovation. However, within the highly regulated

arXiv:2604.27495v1 Announce Type: cross Abstract: Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often

arXiv:2604.27743v1 Announce Type: cross Abstract: We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting IB as