Existing approaches can be categorized into two types. The first type involves leveraging labeled source data for target-domain model selection [9,14-16]. The second type designs unsupervised metrics based on priors of the learned target-domain structure and utilizes the metrics for model selection[17,19,18,20].

Concretely, we propose a coarse-to-fine framework, which starts with acoarsedomain discovery step via progressive domain discriminator training.

Back-translationGiven the low budget and production limitations, this movie is very good.Since it was highly limited in terms of budget, and the production restrictions, the film was cheerful.There are few budget items and production limitations to make this film a really good one.Due to the small dollar amount and production limitations the ouestfilm is very beautiful.Rand Augment

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt learning leverages the power of large-scale pre-trained vision-language models to learn both domain-invariant and specific features through a set of domain-agnostic and domain-specific learnable prompts. Those studies typically enforce invariant constraints on representation, output, or prompt space to learn such prompts. Differently, we cast UDA as a multiple-objective optimization problem in which each objective is represented by a domain loss. Under this new framework, we propose aligning per-objective gradients to foster consensus between them. Additionally, to prevent potential overfitting when fine-tuning this deep learning architecture, we penalize the norm of these gradients. To achieve these goals, we devise a practical gradient update procedure that can work under both single-source and multi-source UDA.

Pairwise evaluation of Large Language Models (LLMs) is a common paradigm, but it is prone to preference bias, where judges systematically favor certain outputs, such as their own. This bias leads to inconsistent and skewed rankings across different judges. To address this, we first empirically demonstrate significant and heterogeneous biases in cross-model evaluations. We then propose UDA (Unsupervised Debiasing Alignment), a framework that reduces inter-judge disagreement by dynamically adjusting the Elo rating system. For each pairwise comparison, a compact neural network learns to adaptively set the K-factor and refine win probabilities. Crucially, UDA operates in a fully unsupervised manner, guided solely by the objective of minimizing the dispersion among the Elo trajectories of all judges. This forces an alignment towards a collective consensus, which serves as an unsupervised proxy for a more stable and reproducible evaluation. In addition, we provide theoretical motivation demonstrating how alignment towards a consensus can reduce aggregate system bias. Experiments show that UDA significantly reduces the inter-judge rating standard deviation by up to 63.4% and improves the average correlation with human judgments by 24.7%. Notably, UDA elevates the performance of poorly performing judges to achieve parity with high-quality ones, fostering a more robust and reliable evaluation ecosystem. Code and data are available at https://anonymous.4open.science/r/62AB93CD-23B4.

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise.

We thank the reviewers for constructive feedback. "Importantly, the number of components is actually decided by the quality of the augmentation operation: an ideal The accuracies of different algorithms are shown in () . Effectively, such a graph has more edges and better connectivity. We will include this detailed explanation in the future version. Please see Figure 1 for an illustration.