Annotated datasets are an essential ingredient to train, evaluate, compare and productionalize supervised machine learning models. It is therefore imperative that annotations are of high quality. For their creation, good quality management and thereby reliable quality estimates are needed. Then, if quality is insufficient during the annotation process, rectifying measures can be taken to improve it. Quality estimation is often performed by having experts manually label instances as correct or incorrect. But checking all annotated instances tends to be expensive. Therefore, in practice, usually only subsets are inspected; sizes are chosen mostly without justification or regard to statistical power and more often than not, are relatively small. Basing estimates on small sample sizes, however, can lead to imprecise values for the error rate. Using unnecessarily large sample sizes costs money that could be better spent, for instance on more annotations. Therefore, we first describe in detail how to use confidence intervals for finding the minimal sample size needed to estimate the annotation error rate. Then, we propose applying acceptance sampling as an alternative to error rate estimation We show that acceptance sampling can reduce the required sample sizes up to 50% while providing the same statistical guarantees.

The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design principles, data minimization has been endorsed by various global data protection regulations. However, its practical implementation remains a challenge due to the lack of a rigorous formulation. This paper addresses this gap and introduces an optimization framework for data minimization based on its legal definitions. It then adapts several optimization algorithms to perform data minimization and conducts a comprehensive evaluation in terms of their compliance with minimization objectives as well as their impact on user privacy. Our analysis underscores the mismatch between the privacy expectations of data minimization and the actual privacy benefits, emphasizing the need for approaches that account for multiple facets of real-world privacy risks.

The neighbor-based method has become a powerful tool to handle the outlier detection problem, which aims to infer the abnormal degree of the sample based on the compactness of the sample and its neighbors. However, the existing methods commonly focus on designing different processes to locate outliers in the dataset, while the contributions of different types neighbors to outlier detection has not been well discussed. To this end, this paper studies the neighbor in the existing outlier detection algorithms and a taxonomy is introduced, which uses the three-level components of information, neighbor and methodology to define hybrid methods. This taxonomy can serve as a paradigm where a novel neighbor-based outlier detection method can be proposed by combining different components in this taxonomy. A large number of comparative experiments were conducted on synthetic and real-world datasets in terms of performance comparison and case study, and the results show that reverse K-nearest neighbor based methods achieve promising performance and dynamic selection method is suitable for working in high-dimensional space. Notably, it is verified that rationally selecting components from this taxonomy may create an algorithms superior to existing methods.

Since the inception of the Transformer architecture in 2017, Large Language Models (LLMs) such as GPT and BERT have evolved significantly, impacting various industries with their advanced capabilities in language understanding and generation. These models have shown potential to transform the medical field, highlighting the necessity for specialized evaluation frameworks to ensure their effective and ethical deployment. This comprehensive survey delineates the extensive application and requisite evaluation of LLMs within healthcare, emphasizing the critical need for empirical validation to fully exploit their capabilities in enhancing healthcare outcomes. Our survey is structured to provide an in-depth analysis of LLM applications across clinical settings, medical text data processing, research, education, and public health awareness. We begin by exploring the roles of LLMs in various medical applications, detailing their evaluation based on performance in tasks such as clinical diagnosis, medical text data processing, information retrieval, data analysis, and educational content generation. The subsequent sections offer a comprehensive discussion on the evaluation methods and metrics employed, including models, evaluators, and comparative experiments. We further examine the benchmarks and datasets utilized in these evaluations, providing a categorized description of benchmarks for tasks like question answering, summarization, information extraction, bioinformatics, information retrieval and general comprehensive benchmarks. This structure ensures a thorough understanding of how LLMs are assessed for their effectiveness, accuracy, usability, and ethical alignment in the medical domain. ...

Table 3 presents the performance results for various models in detecting misclassifications. Our method showed significant improvements over other single-model calibration techniques and the DE method. OOD Detection: A reliable classification model should exhibit higher prediction uncertainty and lower confidence when encountering test samples significantly different from the training data. We assessed different calibration methods' abilities to differentiate OOD samples by blending indistribution test data with OOD data. We assessed two capabilities of models trained on CIFAR-10 and CIFAR-100: far OOD detection and near OOD detection Fort et al. (2019); Hendrycks et al. (2019). Far OOD detection involved distinguishing between CIFAR-10 and SVHN datasets Netzer et al. (2011) for models trained on CIFAR-10, and between CIFAR-100 and SVHN datasets for models trained on CIFAR-100. Near OOD detection required distinguishing between CIFAR-10 and CIFAR-100 datasets, which have similar domains. The results, presented in Table 4, demonstrate significant improvements of our method compared to other single-model calibration methods, even surpassing the performance of the DE method, known for its effectiveness in OOD detection.

AI-generated text detection has attracted increasing attention as powerful language models approach human-level generation. Limited work is devoted to detecting (partially) AI-paraphrased texts. However, AI paraphrasing is commonly employed in various application scenarios for text refinement and diversity. To this end, we propose a novel detection framework, paraphrased text span detection (PTD), aiming to identify paraphrased text spans within a text. Different from text-level detection, PTD takes in the full text and assigns each of the sentences with a score indicating the paraphrasing degree. We construct a dedicated dataset, PASTED, for paraphrased text span detection. Both in-distribution and out-of-distribution results demonstrate the effectiveness of PTD models in identifying AI-paraphrased text spans. Statistical and model analysis explains the crucial role of the surrounding context of the paraphrased text spans. Extensive experiments show that PTD models can generalize to versatile paraphrasing prompts and multiple paraphrased text spans. We release our resources at https://github.com/Linzwcs/PASTED.

Current LLMs are generally aligned to follow safety requirements and tend to refuse toxic prompts. However, LLMs can fail to refuse toxic prompts or be overcautious and refuse benign examples. In addition, state-of-the-art toxicity detectors have low TPRs at low FPR, incurring high costs in real-world applications where toxic examples are rare. In this paper, we explore Moderation Using LLM Introspection (MULI), which detects toxic prompts using the information extracted directly from LLMs themselves. We found significant gaps between benign and toxic prompts in the distribution of alternative refusal responses and in the distribution of the first response token's logits. These gaps can be used to detect toxicities: We show that a toy model based on the logits of specific starting tokens gets reliable performance, while requiring no training or additional computational cost. We build a more robust detector using a sparse logistic regression model on the first response token logits, which greatly exceeds SOTA detectors under multiple metrics.

Creating fair AI systems is a complex problem that involves the assessment of context-dependent bias concerns. Existing research and programming libraries express specific concerns as measures of bias that they aim to constrain or mitigate. In practice, one should explore a wide variety of (sometimes incompatible) measures before deciding which ones warrant corrective action, but their narrow scope means that most new situations can only be examined after devising new measures. In this work, we present a mathematical framework that distils literature measures of bias into building blocks, hereby facilitating new combinations to cover a wide range of fairness concerns, such as classification or recommendation differences across multiple multi-value sensitive attributes (e.g., many genders and races, and their intersections). We show how this framework generalizes existing concepts and present frequently used blocks. We provide an open-source implementation of our framework as a Python library, called FairBench, that facilitates systematic and extensible exploration of potential bias concerns.

Recent end-to-end approaches have shown promise in extending large language models (LLMs) to speech inputs, but face limitations in directly assessing and optimizing alignment quality and fail to achieve fine-grained alignment due to speech-text length mismatch. We introduce BLSP-KD, a novel approach for Bootstrapping Language-Speech Pretraining via Knowledge Distillation, which addresses these limitations through two key techniques. First, it optimizes speech-text alignment by minimizing the divergence between the LLM's next-token prediction distributions for speech and text inputs using knowledge distillation. Second, it employs a continuous-integrate-andfire strategy to segment speech into tokens that correspond one-to-one with text tokens, enabling fine-grained alignment. We also introduce Partial LoRA (PLoRA), a new adaptation method supporting LLM finetuning for speech inputs under knowledge distillation. Quantitative evaluation shows that BLSP-KD outperforms previous end-to-end baselines and cascaded systems with comparable scale of parameters, facilitating general instruction-following capabilities for LLMs with speech inputs. This approach provides new possibilities for extending LLMs to spoken language interactions.

Deferring systems extend supervised Machine Learning (ML) models with the possibility to defer predictions to human experts. However, evaluating the impact of a deferring strategy on system accuracy is still an overlooked area. This paper fills this gap by evaluating deferring systems through a causal lens. We link the potential outcomes framework for causal inference with deferring systems. This allows us to identify the causal impact of the deferring strategy on predictive accuracy. We distinguish two scenarios. In the first one, we can access both the human and the ML model predictions for the deferred instances. In such a case, we can identify the individual causal effects for deferred instances and aggregates of them. In the second scenario, only human predictions are available for the deferred instances. In this case, we can resort to regression discontinuity design to estimate a local causal effect. We empirically evaluate our approach on synthetic and real datasets for seven deferring systems from the literature.