This paper describes the approach of the Unibuc - NLP team in tackling the Coling 2025 GenAI Workshop, Task 1: Binary Multilingual Machine-Generated Text Detection. We explored both masked language models and causal models. For Subtask A, our best model achieved first-place out of 36 teams when looking at F1 Micro (Auxiliary Score) of 0.8333, and second-place when looking at F1 Macro (Main Score) of 0.8301

The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks. This work analyzes existing VLM evaluation techniques, including automated metrics, AIbased assessments, and human evaluations across diverse tasks. We first introduce Robin - a novel suite of VLMs that we built by combining Large Language Models (LLMs) and Vision Encoders (VEs) at multiple scales, and use Robin to identify shortcomings of current evaluation approaches across scales. Next, to overcome the identified limitations, we introduce CHIRP - a new long form response benchmark we developed for more robust and complete VLM evaluation. We provide open access to the Robin training code, model suite, and CHIRP benchmark to promote reproducibility and advance VLM research. Recently, a lot of significant advances have been made in Vision-Language Models (VLMs), driven by breakthroughs in computer vision and natural language processing Chen et al. (2022); Li et al. (2023b); Liu et al. (2023b); Sun et al. (2023). However, existing VLM benchmarks, often designed for specific tasks (e.g., VQAv2 Goyal et al. (2017)), struggle to accurately reflect real-world VLM performance and capture nuanced differences between models Hsieh et al. (2024). This is particularly evident when evaluating models with significant architectural variations, where standard benchmark scores remain similar despite noticeable differences in human-perceived model quality. To address this issue, we introduce CHIRP, a hybrid VLM benchmark that combines automated metrics' scalability with human evaluators' nuanced judgment. We argue that this approach is crucial for capturing the complexities of VLM behavior, which traditional benchmarks often fail to represent. To demonstrate the limitations of existing benchmarks and the efficacy of our proposed method, we introduce Robin, a suite of VLMs trained at various scales, inspired by the Pythia language model suite Biderman et al. (2023). By systematically varying the Vision Encoder (VE) and the Large Language Model (LLM) sizes, we will show that while benchmark scores remain largely unaffected, human evaluations reveal significant differences in the models' outputs quality. Our findings underscore the need for more robust and human-centric VLM evaluation methodologies. CHIRP paves the way for developing more reliable and informative VLM benchmarks, ultimately leading to the creation of more effective and impactful VLMs. Our Contributions: We investigate the drawbacks of relying on automatic metrics and show the benefits of AI-based and human-based evaluations of VLMs. We train and release an open-source collection of VLMs named Robin. Robin is a scaling suite based on LLMs and VEs of different sizes.

As artificial intelligence (AI) becomes increasingly embedded in healthcare delivery, this chapter explores the critical aspects of developing reliable and ethical Clinical Decision Support Systems (CDSS). Beginning with the fundamental transition from traditional statistical models to sophisticated machine learning approaches, this work examines rigorous validation strategies and performance assessment methods, including the crucial role of model calibration and decision curve analysis. The chapter emphasizes that creating trustworthy AI systems in healthcare requires more than just technical accuracy; it demands careful consideration of fairness, explainability, and privacy. The challenge of ensuring equitable healthcare delivery through AI is stressed, discussing methods to identify and mitigate bias in clinical predictive models. The chapter then delves into explainability as a cornerstone of human-centered CDSS. This focus reflects the understanding that healthcare professionals must not only trust AI recommendations but also comprehend their underlying reasoning. The discussion advances in an analysis of privacy vulnerabilities in medical AI systems, from data leakage in deep learning models to sophisticated attacks against model explanations. The text explores privacy-preservation strategies such as differential privacy and federated learning, while acknowledging the inherent trade-offs between privacy protection and model performance. This progression, from technical validation to ethical considerations, reflects the multifaceted challenges of developing AI systems that can be seamlessly and reliably integrated into daily clinical practice while maintaining the highest standards of patient care and data protection.

Text-to-SQL enables users to interact with databases through natural language, simplifying the retrieval and synthesis of information. Despite the success of large language models (LLMs) in converting natural language questions into SQL queries, their broader adoption is limited by two main challenges: achieving robust generalization across diverse queries and ensuring interpretative confidence in their predictions. To tackle these issues, our research investigates the integration of selective classifiers into Text-to-SQL systems. We analyse the trade-off between coverage and risk using entropy based confidence estimation with selective classifiers and assess its impact on the overall performance of Text-to-SQL models. Additionally, we explore the models' initial calibration and improve it with calibration techniques for better model alignment between confidence and accuracy. Our experimental results show that encoder-decoder T5 is better calibrated than in-context-learning GPT 4 and decoder-only Llama 3, thus the designated external entropy-based selective classifier has better performance. The study also reveal that, in terms of error detection, selective classifier with a higher probability detects errors associated with irrelevant questions rather than incorrect query generations.

Abstract: Background: Understanding cardiovascular artery disease risk factors, the leading global cause of mortality, is crucial for influencing its etiology, prevalence, and treatment. This study aims to evaluate prognostic markers for coronary artery disease in Mashhad using Naive Bayes, REP Tree, J48, CART, and CHAID algorithms. Methods: Using data from the 2009 MASHAD STUDY, prognostic factors for coronary artery disease were determined with Naive Bayes, REP Tree, J48, CART, CHAID, and Random Forest algorithms using R 3.5.3 and WEKA 3.9.4. Model efficiency was compared by sensitivity, specificity, and accuracy. Cases were patients with coronary artery disease; each had three controls (totally 940). Results: Prognostic factors for coronary artery disease in Mashhad residents varied by algorithm. CHAID identified age, myocardial infarction history, and hypertension. CART included depression score and physical activity. REP added education level and anxiety score. NB included diabetes and family history. J48 highlighted father's heart disease and weight loss. CHAID had the highest accuracy (0.80). Conclusion: Key prognostic factors for coronary artery disease in CART and CHAID models include age, myocardial infarction history, hypertension, depression score, physical activity, and BMI. NB, REP Tree, and J48 identified numerous factors. CHAID had the highest accuracy, sensitivity, and specificity. CART offers simpler interpretation, aiding physician and paramedic model selection based on specific. Keywords: RF, Na\"ive Bayes, REP, J48 algorithms, Coronary Artery Disease (CAD).

Detecting object-level changes between two images across possibly different views is a core task in many applications that involve visual inspection or camera surveillance. Existing change-detection approaches suffer from three major limitations: (1) lack of evaluation on image pairs that contain no changes, leading to unreported false positive rates; (2) lack of correspondences (i.e., localizing the regions before and after a change); and (3) poor zero-shot generalization across different domains. To address these issues, we introduce a novel method that leverages change correspondences (a) during training to improve change detection accuracy, and (b) at test time, to minimize false positives. That is, we harness the supervision labels of where an object is added or removed to supervise change detectors, improving their accuracy over previous work by a large margin. Our work is also the first to predict correspondences between pairs of detected changes using estimated homography and the Hungarian algorithm. Our model demonstrates superior performance over existing methods, achieving state-of-the-art results in change detection and change correspondence accuracy across both in-distribution and zero-shot benchmarks.

Diagnosis of ice accretion on wind turbine blades is all the time a hard nut to crack in condition monitoring of wind farms. Existing methods focus on mechanism analysis of icing process, deviation degree analysis of feature engineering. However, there have not been deep researches of neural networks applied in this field at present. Supervisory control and data acquisition (SCADA) makes it possible to train networks through continuously providing not only operation parameters and performance parameters of wind turbines but also environmental parameters and operation modes. This paper explores the possibility that using convolutional neural networks (CNNs), generative adversarial networks (GANs) and domain adaption learning to establish intelligent diagnosis frameworks under different training scenarios. Specifically, PGANC and PGANT are proposed for sufficient and non-sufficient target wind turbine labeled data, respectively. The basic idea is that we consider a two-stage training with parallel GANs, which are aimed at capturing intrinsic features for normal and icing samples, followed by classification CNN or domain adaption module in various training cases. Model validation on three wind turbine SCADA data shows that two-stage training can effectively improve the model performance. Besides, if there is no sufficient labeled data for a target turbine, which is an extremely common phenomenon in real industrial practices, the addition of domain adaption learning makes the trained model show better performance. Overall, our proposed intelligent diagnosis frameworks can achieve more accurate detection on the same wind turbine and more generalized capability on a new wind turbine, compared with other machine learning models and conventional CNNs.

In high-dimensional regression, feature selection methods, such as sequential feature selection (SeqFS), are commonly used to identify relevant features. When data is limited, domain adaptation (DA) becomes crucial for transferring knowledge from a related source domain to a target domain, improving generalization performance. Although SeqFS after DA is an important task in machine learning, none of the existing methods can guarantee the reliability of its results. In this paper, we propose a novel method for testing the features selected by SeqFS-DA. The main advantage of the proposed method is its capability to control the false positive rate (FPR) below a significance level $\alpha$ (e.g., 0.05). Additionally, a strategic approach is introduced to enhance the statistical power of the test. Furthermore, we provide extensions of the proposed method to SeqFS with model selection criteria including AIC, BIC, and adjusted R-squared. Extensive experiments are conducted on both synthetic and real-world datasets to validate the theoretical results and demonstrate the proposed method's superior performance.

The F-measure is an important and commonly used performance metric for binary prediction tasks. By combining precision and recall into a single score, it avoids disadvantages of simple metrics like the error rate, especially in cases of imbalanced class distributions. The problem of optimizing the F-measure, that is, of developing learning algorithms that perform optimally in the sense of this measure, has recently been tackled by several authors. In this paper, we study the problem of F-measure maximization in the setting of online learning. We propose an efficient online algorithm and provide a formal analysis of its convergence properties.

Given an unsupervised novelty detection task on a new dataset, how can we automatically select a ''best'' detection model while simultaneously controlling the error rate of the best model? For novelty detection analysis, numerous detectors have been proposed to detect outliers on a new unseen dataset based on a score function trained on available clean data. However, due to the absence of labeled data for model evaluation and comparison, there is a lack of systematic approaches that are able to select a ''best'' model/detector (i.e., the algorithm as well as its hyperparameters) and achieve certain error rate control simultaneously. In this paper, we introduce a unified data-driven procedure to address this issue. The key idea is to maximize the number of detected outliers while controlling the false discovery rate (FDR) with the help of Jackknife prediction. We establish non-asymptotic bounds for the false discovery proportions and show that the proposed procedure yields valid FDR control under some mild conditions.