As large language models (LLMs) increasingly imitate personal writing styles, personalization has become a key challenge for machine-generated text (MGT) detection. Yet personalized MGT detection remains largely underexplored. In this work, we introduce StyloBench, the first benchmark for evaluating detector robustness under personalization, built from literary and blog texts paired with their LLM-generated imitations. Experiments across diverse detectors show pronounced performance instability under personalization, with frequent inversions relative to general-domain behavior. To better understand this limitation, we conduct an in-depth analysis and attribute it to a feature-inversion trap, i.e., features that are effective for separating human-written text (HWT) from MGT in general flip their effect in personalized contexts, ultimately misleading detectors. Motivated by this, we propose StyloCheck, a diagnostic framework for predicting detector robustness under personalization. StyloCheck identifies the inverted features and quantifies detector dependence using perturbed texts pronounced in the features. In our experiments, StyloCheck predicts both the direction and magnitude of cross-domain performance shifts with an 85% correlation to actual outcomes. We hope this work will raise awareness of the structural risks introduced by personalization and motivate more robust approaches to personalized MGT detection. The code is available at: https://github.com/mbzuai-nlp/Personalized_MGT_Detect

Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks.However, their performance on paid, real-world design projects remains uncertain. We introduce ServImage, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) ServImageBench: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over $295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations.(ii) ServImageScore: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable.(iii) ServImageModel: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00% accuracy in predicting human payment decisions and producing calibrated payment probabilities.ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems Github.

This paper presents StateCloud’s submission to the Critical Questions Generation (CQs-Gen) shared task at the Argument Mining Workshop 2025. To generate high-quality critical questions from argumentative texts, we propose a framework that combines prompt engineering with few-shot learning to effectively guide generative models. Additionally, we ensemble outputs from diverse large language models (LLMs) to enhance accuracy. Notably, our approach achieved 3rd place in the competition, demonstrating the viability of prompt engineering strategies for argumentative tasks.

Cross-lingual emotion detection faces challenges such as imbalanced label distribution, data scarcity, cultural and linguistic differences, figurative language, and the opaqueness of pre-trained language models. This paper presents our approach to the EXALT shared task at WASSA 2024, focusing on emotion transferability across languages and trigger word identification. We employ data augmentation techniques, including back-translation and synonym replacement, to address data scarcity and imbalance issues in the emotion detection sub-task. For the emotion trigger identification sub-task, we utilize token and label mapping to capture emotional information at the subword level. Our system achieves competitive performance, ranking 13th, 1st, and 2nd in the Emotion Detection, Binary Trigger Word Detection, and Numerical Trigger Word Detection tasks.

Lay summaries play a crucial role in making scientific research accessible to a wider audience. However, generating lay summaries from lengthy articles poses significant challenges. We consider two approaches to address this issue: Hard Truncation, which preserves the most informative initial portion of the article, and Text Chunking, which segments articles into smaller, manageable chunks. Our workflow encompasses data preprocessing, augmentation, prompt engineering, and fine-tuning large language models. We explore the influence of pretrained model selection, inference prompt design, and hyperparameter tuning on summarization performance. Our methods demonstrate effectiveness in generating high-quality, informative lay summaries, achieving the second-best performance in the BioLaySumm shared task at BioNLP 2024.

Emotion classification on code-mixed text messages is challenging due to the multilingual languages and non-literal cues (i.e., emoticons). To solve these problems, we propose an innovative soft prompt tuning method, which is lightweight and effective to release potential abilities of the pre-trained language models and improve the classification results. Firstly, we transform emoticons into textual information to utilize their rich emotional information. Then, variety of innovative templates and verbalizers are applied to promote emotion classification. Extensive experiments show that transforming emoticons and employing prompt tuning both benefit the performance. Finally, as a part of WASSA 2023, we obtain the accuracy of 0.972 in track MLEC and 0.892 in track MCEC, yielding the second place in both two tracks.