In this work, we address the problem of controlling a classifier's accuracy at any user-specified level through selective classification, regardless of the problem's inherent difficulty. Traditional classification frameworks are designed to approximate the Bayes optimal error rate as closely as possible. However, with the growing deployment of artificial intelligence (AI) systems in automated, high-stakes decision-making, it has become critical to ensure reliable control over a classifier's accuracy and to guarantee accurate predictions for all individuals. When the underlying problem is truly difficult, as indicated by the distance between the true distributions for each decision class, achieving control over the error rate of an automated decisionmaking system may be impossible. This is particularly true when the number of potential classes is large or when the distributions of these classes are close enough, significantly increasing the difficulty of the problem. This phenomenon is illustrated in Figure 1, where the task is to classify various observations as High-Risk or Low-Risk, while maintaining an error rate below 5%. In this example, the High-Risk and Low-Risk classes are modeled as mixtures of two normal distributions with means of 2 and 1, respectively, and a shared variance of 1. The Bayes classifier is represented by the dotted line in the leftmost plot of Figure 1. In this scenario, the Bayes optimal error rate is 15.9%, significantly exceeding our target classification error of 5%.

Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How to optimally operate watermarkers in adversarial environments? To fill this gap, we systematize existing LLM watermarkers and watermark removal attacks, mapping out their design spaces. We then develop WaterPark, a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks. More importantly, by leveraging WaterPark, we conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness. We further explore the best practices to operate watermarkers in adversarial environments. We believe our study sheds light on current LLM watermarking techniques while WaterPark serves as a valuable testbed to facilitate future research.

Advanced large language models (LLMs) can generate text almost indistinguishable from human-written text, highlighting the importance of LLM-generated text detection. However, current zero-shot techniques face challenges as white-box methods are restricted to use weaker open-source LLMs, and black-box methods are limited by partial observation from stronger proprietary LLMs. It seems impossible to enable white-box methods to use proprietary models because API-level access to the models neither provides full predictive distributions nor inner embeddings. To traverse the divide, we propose Glimpse, a probability distribution estimation approach, predicting the full distributions from partial observations. Despite the simplicity of Glimpse, we successfully extend white-box methods like Entropy, Rank, Log-Rank, and Fast-DetectGPT to latest proprietary models. Experiments show that Glimpse with Fast-DetectGPT and GPT-3.5 achieves an average AUROC of about 0.95 in five latest source models, improving the score by 51% relative to the remaining space of the open source baseline (Table 1). It demonstrates that the latest LLMs can effectively detect their own outputs, suggesting that advanced LLMs may be the best shield against themselves.

As social systems become increasingly complex, legal articles are also growing more intricate, making it progressively harder for humans to identify any potential competitions among them, particularly when drafting new laws or applying existing laws. Despite this challenge, no method for detecting such competitions has been proposed so far. In this paper, we propose a new legal AI task called Legal Article Competition Detection (LACD), which aims to identify competing articles within a given law. Our novel retrieval method, CAM-Re2, outperforms existing relevant methods, reducing false positives by 20.8% and false negatives by 8.3%, while achieving a 98.2% improvement in precision@5, for the LACD task. We release our codes at https://github.com/asmath472/LACD-public.

The goal of this project is to classify four different insect sounds: cicada, beetle, termite, and cricket. One application of this project is for pest control to monitor and protect our ecosystem. Our project leverages data augmentation, including pitch shifting and speed changing, to improve model generalization. This project will test the performance of Decision Tree, Random Forest, SVM RBF, XGBoost, and k-NN models, combined with MFCC feature. A potential novelty of this project is that various data augmentation techniques are used and created 6 data along with the original sound. The dataset consists of the sound recordings of these four insects. This project aims to achieve a high classification accuracy and to reduce the over-fitting problem.

This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility. One focus of this work is sharpness-aware training (SAT) and its integration with differential privacy (DP-SAT) to further improve this balance. Additionally, we examine fairness in both private and non-private learning models trained on datasets with synthetic and real-world biases. We also measure the privacy risks involved in these scenarios by performing membership inference attacks (MIAs) and explore the consequences of eliminating high-privacy risk samples, termed outliers. Moreover, we introduce a new metric, named \emph{harmonic score}, which combines accuracy, privacy, and fairness into a single measure. Through empirical analysis using generalization techniques, we achieve an accuracy of 81.11\% under $(8, 10^{-5})$-DP on CIFAR-10, surpassing the 79.5\% reported by De et al. (2022). Moreover, our experiments show that memorization of training samples can begin before the overfitting point, and generalization techniques do not guarantee the prevention of this memorization. Our analysis of synthetic biases shows that generalization techniques can amplify model bias in both private and non-private models. Additionally, our results indicate that increased bias in training data leads to reduced accuracy, greater vulnerability to privacy attacks, and higher model bias. We validate these findings with the CelebA dataset, demonstrating that similar trends persist with real-world attribute imbalances. Finally, our experiments show that removing outlier data decreases accuracy and further amplifies model bias.

Mathematical reasoning, a core aspect of human cognition, is vital across many domains, from educational problem-solving to scientific advancements. As artificial general intelligence (AGI) progresses, integrating large language models (LLMs) with mathematical reasoning tasks is becoming increasingly significant. This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models (MLLMs). We review over 200 studies published since 2021, and examine the state-of-the-art developments in Math-LLMs, with a focus on multimodal settings. We categorize the field into three dimensions: benchmarks, methodologies, and challenges. In particular, we explore multimodal mathematical reasoning pipeline, as well as the role of (M)LLMs and the associated methodologies. Finally, we identify five major challenges hindering the realization of AGI in this domain, offering insights into the future direction for enhancing multimodal reasoning capabilities. This survey serves as a critical resource for the research community in advancing the capabilities of LLMs to tackle complex multimodal reasoning tasks.

Pediatric Emergency Department (PED) overcrowding presents a significant global challenge, prompting the need for efficient solutions. This paper introduces the BioBridge framework, a novel approach that applies Natural Language Processing (NLP) to Electronic Medical Records (EMRs) in written free-text form to enhance decision-making in PED. In non-English speaking countries, such as South Korea, EMR data is often written in a Code-Switching (CS) format that mixes the native language with English, with most code-switched English words having clinical significance. The BioBridge framework consists of two core modules: "bridging modality in context" and "unified bio-embedding." The "bridging modality in context" module improves the contextual understanding of bilingual and code-switched EMRs. In the "unified bio-embedding" module, the knowledge of the model trained in the medical domain is injected into the encoder-based model to bridge the gap between the medical and general domains. Experimental results demonstrate that the proposed BioBridge significantly performance traditional machine learning and pre-trained encoder-based models on several metrics, including F1 score, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and Brier score. Specifically, BioBridge-XLM achieved enhancements of 0.85% in F1 score, 0.75% in AUROC, and 0.76% in AUPRC, along with a notable 3.04% decrease in the Brier score, demonstrating marked improvements in accuracy, reliability, and prediction calibration over the baseline XLM model. The source code will be made publicly available.

WARNING: This paper contains content that maybe upsetting or offensive to some readers. Dog whistles are coded expressions with dual meanings: one intended for the general public (outgroup) and another that conveys a specific message to an intended audience (ingroup). Often, these expressions are used to convey controversial political opinions while maintaining plausible deniability and slip by content moderation filters. Identification of dog whistles relies on curated lexicons, which have trouble keeping up to date. We introduce \textbf{FETCH!}, a task for finding novel dog whistles in massive social media corpora. We find that state-of-the-art systems fail to achieve meaningful results across three distinct social media case studies. We present \textbf{EarShot}, a novel system that combines the strengths of vector databases and Large Language Models (LLMs) to efficiently and effectively identify new dog whistles.

Automated task guidance has recently attracted attention from the AI research community. Procedural mistake detection (PMD) is a challenging sub-problem of classifying whether a human user (observed through egocentric video) has successfully executed the task at hand (specified by a procedural text). Despite significant efforts in building resources and models for PMD, machine performance remains nonviable, and the reasoning processes underlying this performance are opaque. As such, we recast PMD to an explanatory self-dialog of questions and answers, which serve as evidence for a decision. As this reformulation enables an unprecedented transparency, we leverage a fine-tuned natural language inference (NLI) model to formulate two automated coherence metrics for generated explanations. Our results show that while open-source VLMs struggle with this task off-the-shelf, their accuracy, coherence, and dialog efficiency can be vastly improved by incorporating these coherence metrics into common inference and fine-tuning methods. Furthermore, our multi-faceted metrics can visualize common outcomes at a glance, highlighting areas for improvement.