Withincreasingscale,outliersbecome more and more common in all layers of the transformer, and they occur in almost all sequence dimensions.

Eachd2 Dis sentences, follows: 1. StartwithD =;. 2. ForeachchromosomeC, repeat (a) Pickuniformlyqbetween end.

Ouranalysis culminates inshowing thatthere exists a universally consistent histogram-style estimator that converges to any multi-view model with a finite number of Lipschitz continuous components at a rate of eO(1/3 n) in L1 error.

We conduct a preliminary study on finding a proper prompt construction strategy. Further research can utilize our analysis to construct more powerful code prompts. Table 1: Code prompt study results of CBS. N" means there are one human-relevant function Table 2: Automatic and human evaluation results of social biases in the generated code on GPT -4. We also conduct experiments on GPT -4.

Abstract--The widespread adoption of large language models (LLMs) has made it difficult to distinguish human writing from machine-produced text in many real applications. Detectors that were effective for one generation of models tend to degrade when newer models or modified decoding strategies are introduced. In this work, we study this lack of stability and propose a hybrid ensemble that is explicitly designed to cope with changing generator distributions. The ensemble combines three complementary components: a RoBERT a-based classifier fine-tuned for supervised detection, a curvature-inspired score based on perturbing the input and measuring changes in model likelihood, and a compact stylometric model built on handcrafted linguistic features. The outputs of these components are fused on the probability simplex, and the weights are chosen via validation-based search. We frame this approach in terms of variance reduction and risk under mixtures of generators, and show that the simplex constraint provides a simple way to trade off the strengths and weaknesses of each branch. Experiments on a 30 000-document corpus drawn from several LLM families including models unseen during training and paraphrased attack variants show that the proposed method achieves 94.2% accuracy and an AUC of 0.978. The ensemble also lowers false positives on scientific articles compared to strong baselines, which is critical in educational and research settings where wrongly flagging human work is costly. Text generated by large language models (LLMs) is now routinely used in homework, reports, programming, and informal communication.

Phishing is a cybercrime in which individuals are deceived into revealing personal information, often resulting in financial loss. These attacks commonly occur through fraudulent messages, misleading advertisements, and compromised legitimate websites. This study proposes a Quantile Regression Deep Q-Network (QR-DQN) approach that integrates RoBERTa semantic embeddings with handcrafted lexical features to enhance phishing detection while accounting for uncertainties. Unlike traditional DQN methods that estimate single scalar Q-values, QR-DQN leverages quantile regression to model the distribution of returns, improving stability and generalization on unseen phishing data. A diverse dataset of 105,000 URLs was curated from PhishTank, OpenPhish, Cloudflare, and other sources, and the model was evaluated using an 80/20 train-test split. The QR-DQN framework achieved a test accuracy of 99.86%, precision of 99.75%, recall of 99.96%, and F1-score of 99.85%, demonstrating high effectiveness. Compared to standard DQN with lexical features, the hybrid QR-DQN with lexical and semantic features reduced the generalization gap from 1.66% to 0.04%, indicating significant improvement in robustness. Five-fold cross-validation confirmed model reliability, yielding a mean accuracy of 99.90% with a standard deviation of 0.04%. These results suggest that the proposed hybrid approach effectively identifies phishing threats, adapts to evolving attack strategies, and generalizes well to unseen data.

We present an evaluation-driven study of two practical tasks regarding online misinformation: (i) fake-news detection and (ii) virality prediction in the context of operational settings, with the necessity for rapid reaction. Using the EVONS and FakeNewsNet datasets, we compare textual embeddings (RoBERTa; with a control using Mistral) against lightweight numeric features (timing, follower counts, verification, likes) and sequence models (GRU, gating architectures, Transformer encoders). We show that textual content alone is a strong discriminator for fake-news detection, while numeric-only pipelines remain viable when language models are unavailable or compute is constrained. Virality prediction is markedly harder than fake-news detection and is highly sensitive to label construction; in our setup, a median-based ''viral'' split (<50 likes) is pragmatic but underestimates real-world virality, and time-censoring for engagement features is desirable yet difficult under current API limits. Dimensionality-reduction analyses suggest non-linear structure is more informative for virality than for fake-news detection (t-SNE > PCA on numeric features). Swapping RoBERTa for Mistral embeddings yields only modest deltas, leaving conclusions unchanged. We discuss implications for evaluation design and report reproducibility constraints that realistically affect the field. We release splits and code where possible and provide guidance for metric selection.

Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants remain underexplored. We provide the first comprehensive study grounding ID in interpretable text properties through cross-encoder analysis, linguistic features, and sparse autoencoders (SAEs). In this work, we establish three key findings. First, ID is complementary to entropy-based metrics: after controlling for length, the two are uncorrelated, with ID capturing geometric complexity orthogonal to prediction quality. Second, ID exhibits robust genre stratification: scientific prose shows low ID (~8), encyclopedic content medium ID (~9), and creative/opinion writing high ID (~10.5) across all models tested. This reveals that contemporary LLMs find scientific text "representationally simple" while fiction requires additional degrees of freedom. Third, using SAEs, we identify causal features: scientific signals (formal tone, report templates, statistics) reduce ID; humanized signals (personalization, emotion, narrative) increase it. Steering experiments confirm these effects are causal. Thus, for contemporary models, scientific writing appears comparatively "easy", whereas fiction, opinion, and affect add representational degrees of freedom. Our multi-faceted analysis provides practical guidance for the proper use of ID and the sound interpretation of ID-based results.