Inthispaper,wepropose a tractable algorithm that estimates the probabilistic aggregation map from the system'strajectory.

This paper describes EmoRAG, a system designed to detect perceived emotions in text for SemEval-2025 Task 11, Subtask A: Multi-label Emotion Detection. We focus on predicting the perceived emotions of the speaker from a given text snippet, labeling it with emotions such as joy, sadness, fear, anger, surprise, and disgust. Our approach does not require additional model training and only uses an ensemble of models to predict emotions. EmoRAG achieves results comparable to the best performing systems, while being more efficient, scalable, and easier to implement.

Gaussian process (GP) models have received increasingly attentions in recent years due to their superb prediction accuracy and modeling flexibility. To address the computational burdens of GP models for large-scale datasets, distributed learning for GPs are often adopted. Current aggregation models for distributed GPs are not time-efficient when incorporating correlations between GP experts. In this work, we propose a novel approach for aggregated prediction in distributed GPs. The technique is suitable for both the exact and sparse variational GPs. The proposed method incorporates correlations among experts, leading to better prediction accuracy with manageable computational requirements. As demonstrated by empirical studies, the proposed approach results in more stable predictions in less time than state-of-the-art consistent aggregation models.

Despite recent advances in AI and machine learning technologies, many applications still require human assessment because the characteristics of objects that can explain human subjectivity are sometimes unknown or too vague to be extracted automatically, which is a serious bottleneck when conducting large-scale automated quality assessments. The use of crowdsourcing is a promising way to implement this with the wisdom of the crowd. One challenge in crowdsourced quality assessments is the uncertainty of human judgments. Since workers have different competences, expertise, or motivations, their responses are sometimes too noisy to analyze and extract useful knowledge. A straightforward solution is to assign multiple crowdworkers to each evaluation target and aggregate the redundantly collected evaluations using majority voting. More sophisticated statistical methods, such as Bayesian generative models, have also been explored for better aggregations. Various factors of human error have been introduced into statistical models, such as the ability of workers (Dawid & Skene, 1979), difficulty of the questions (Whitehill et al., 2009; Welinder et al., 2011), and presence of malicious workers (Raykar & Yu, 2011).

In recent years, the neural network backdoor hidden in the parameters of the federated learning model has been proved to have great security risks. Considering the characteristics of trigger generation, data poisoning and model training in backdoor attack, this paper designs a backdoor attack method based on federated learning. Firstly, aiming at the concealment of the backdoor trigger, a TrojanGan steganography model with encoder-decoder structure is designed. The model can encode specific attack information as invisible noise and attach it to the image as a backdoor trigger, which improves the concealment and data transformations of the backdoor trigger.Secondly, aiming at the problem of single backdoor trigger mode, an image poisoning attack method called combination trigger attack is proposed. This method realizes multi-backdoor triggering by multiplexing combined triggers and improves the robustness of backdoor attacks. Finally, aiming at the problem that the local training mechanism leads to the decrease of the success rate of backdoor attack, a dual model replacement backdoor attack algorithm based on federated learning is designed. This method can improve the success rate of backdoor attack while maintaining the performance of the federated learning aggregation model. Experiments show that the attack strategy in this paper can not only achieve high backdoor concealment and diversification of trigger forms under federated learning, but also achieve good attack success rate in multi-target attacks.door concealment and diversification of trigger forms but also achieve good results in multi-target attacks.

Whether Large Language Models (LLMs) can outperform crowdsourcing on the data annotation task is attracting interest recently. Some works verified this issue with the average performance of individual crowd workers and LLM workers on some specific NLP tasks by collecting new datasets. However, on the one hand, existing datasets for the studies of annotation quality in crowdsourcing are not yet utilized in such evaluations, which potentially provide reliable evaluations from a different viewpoint. On the other hand, the quality of these aggregated labels is crucial because, when utilizing crowdsourcing, the estimated labels aggregated from multiple crowd labels to the same instances are the eventually collected labels. Therefore, in this paper, we first investigate which existing crowdsourcing datasets can be used for a comparative study and create a benchmark. We then compare the quality between individual crowd labels and LLM labels and make the evaluations on the aggregated labels. In addition, we propose a Crowd-LLM hybrid label aggregation method and verify the performance. We find that adding LLM labels from good LLMs to existing crowdsourcing datasets can enhance the quality of the aggregated labels of the datasets, which is also higher than the quality of LLM labels themselves.

Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A strategy to improve label quality is to ask multiple annotators to label the same item and aggregate their labels. Many aggregation models have been proposed for categorical or numerical annotation tasks, but far less work has considered more complex annotation tasks involving open-ended, multivariate, or structured responses. While a variety of bespoke models have been proposed for specific tasks, our work is the first to introduce aggregation methods that generalize across many diverse complex tasks, including sequence labeling, translation, syntactic parsing, ranking, bounding boxes, and keypoints. This generality is achieved by devising a task-agnostic method to model distances between labels rather than the labels themselves. This article extends our prior work with investigation of three new research questions. First, how do complex annotation properties impact aggregation accuracy? Second, how should a task owner navigate the many modeling choices to maximize aggregation accuracy? Finally, what diagnoses can verify that aggregation models are specified correctly for the given data? To understand how various factors impact accuracy and to inform model selection, we conduct simulation studies and experiments on real, complex datasets. Regarding testing, we introduce unit tests for aggregation models and present a suite of such tests to ensure that a given model is not mis-specified and exhibits expected behavior. Beyond investigating these research questions above, we discuss the foundational concept of annotation complexity, present a new aggregation model as a bridge between traditional models and our own, and contribute a new semi-supervised learning method for complex label aggregation that outperforms prior work.

Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A common strategy to improve label quality is to ask multiple annotators to label the same item and then aggregate their labels. To date, many aggregation models have been proposed for simple categorical or numerical annotation tasks, but far less work has considered more complex annotation tasks, such as those involving open-ended, multivariate, or structured responses. Similarly, while a variety of bespoke models have been proposed for specific tasks, our work is the first we are aware of to introduce aggregation methods that generalize across many, diverse complex tasks, including sequence labeling, translation, syntactic parsing, ranking, bounding boxes, and keypoints. This generality is achieved by applying readily available task-specific distance functions, then devising a task-agnostic method to model these distances between labels, rather than the labels themselves. This article presents a unified treatment of our prior work on complex annotation modeling and extends that work with investigation of three new research questions. First, how do complex annotation task and dataset properties impact aggregation accuracy? Second, how should a task owner navigate the many modeling choices in order to maximize aggregation accuracy? Finally, what tests and diagnoses can verify that aggregation models are specified correctly for the given data? To understand how various factors impact accuracy and to inform model selection, we conduct large-scale simulation studies and broad experiments on real, complex datasets. Regarding testing, we introduce the concept of unit tests for aggregation models and present a suite of such tests to ensure that a given model is not mis-specified and exhibits expected behavior. Beyond investigating these research questions above, we discuss the foundational concept and nature of annotation complexity, present a new aggregation model as a conceptual bridge between traditional models and our own, and contribute a new general semisupervised learning method for complex label aggregation that outperforms prior work.

Recent advancements in transformer-based speech representation models have greatly transformed speech processing. However, there has been limited research conducted on evaluating these models for speech emotion recognition (SER) across multiple languages and examining their internal representations. This article addresses these gaps by presenting a comprehensive benchmark for SER with eight speech representation models and six different languages. We conducted probing experiments to gain insights into inner workings of these models for SER. We find that using features from a single optimal layer of a speech model reduces the error rate by 32\% on average across seven datasets when compared to systems where features from all layers of speech models are used. We also achieve state-of-the-art results for German and Persian languages. Our probing results indicate that the middle layers of speech models capture the most important emotional information for speech emotion recognition.

The aggregation of multiple opinions plays a crucial role in decision-making, such as in hiring and loan review, and in labeling data for supervised learning. Although majority voting and existing opinion aggregation models are effective for simple tasks, they are inappropriate for tasks without objectively true labels in which disagreements may occur. In particular, when voter attributes such as gender or race introduce bias into opinions, the aggregation results may vary depending on the composition of voter attributes. A balanced group of voters is desirable for fair aggregation results but may be difficult to prepare. In this study, we consider methods to achieve fair opinion aggregation based on voter attributes and evaluate the fairness of the aggregated results. To this end, we consider an approach that combines opinion aggregation models such as majority voting and the Dawid and Skene model (D&S model) with fairness options such as sample weighting. To evaluate the fairness of opinion aggregation, probabilistic soft labels are preferred over discrete class labels. First, we address the problem of soft label estimation without considering voter attributes and identify some issues with the D&S model. To address these limitations, we propose a new Soft D&S model with improved accuracy in estimating soft labels. Moreover, we evaluated the fairness of an opinion aggregation model, including Soft D&S, in combination with different fairness options using synthetic and semi-synthetic data. The experimental results suggest that the combination of Soft D&S and data splitting as a fairness option is effective for dense data, whereas weighted majority voting is effective for sparse data. These findings should prove particularly valuable in supporting decision-making by human and machine-learning models with balanced opinion aggregation.