arXiv:2505.16690v5 Announce Type: replace Abstract: Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trained language models (PoLMs) often suffer from over-confidence,…
arXiv:2511.19497v1 Announce Type: new Abstract: The attention mechanism has demonstrated remarkable potential in sequence modeling, exemplified by its successful application in natural language processing with models such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT). Despite…
arXiv:2508.11086v3 Announce Type: replace Abstract: Watch time is widely used as a proxy for user satisfaction in video recommendation platforms. However, raw watch times are influenced by confounding factors such as video duration, popularity, and individual user behaviors, potentially distorting…
arXiv:2511.19498v1 Announce Type: new Abstract: Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks due to training data memorization, particularly within healthcare contexts involving imperfect or privacy-sensitive patient information. We present a hierarchical dual-strategy framework for selective…
arXiv:2511.04774v3 Announce Type: replace Abstract: Large-scale networked services rely on deep soft-ware stacks and microservice orchestration, which increase instruction footprints and create frontend stalls that inflate tail latency and energy. We revisit instruction prefetching for these cloud workloads and present…
arXiv:2511.19499v1 Announce Type: new Abstract: The rapid advancement of generators (e.g., StyleGAN, Midjourney, DALL-E) has produced highly realistic synthetic images, posing significant challenges to digital media authenticity. These generators are typically based on a few core architectural families, primarily Generative…
arXiv:2410.13334v5 Announce Type: replace-cross Abstract: Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks’, where malicious inputs can coerce LLMs into generating harmful content bypassing safety alignments. In this paper,…
arXiv:2511.19504v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fairness, scaling to diverse populations becomes computationally intractable, and making systems…
arXiv:2505.13902v3 Announce Type: replace-cross Abstract: In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variables are singular, for which conventional…
arXiv:2511.19506v1 Announce Type: new Abstract: Mental health disorders, particularly cognitive disorders defined by deficits in cognitive abilities, are described in detail in the DSM-5, which includes definitions and examples of signs and symptoms. A simplified, machine-actionable representation was developed to…
