The investigation of legal judgment prediction (LJP), such as sentencing prediction, has attracted broad attention for its potential to promote judicial fairness, making the accuracy and reliability of its computation result an increasingly critical concern. In view of this, we present a new sentencing model that shares both legal logic interpretability and strong prediction capability by introducing a two-stage learning algorithm. Specifically, we first construct a hybrid model that synthesizes a mechanism model based on the main factors for sentencing with a neural network modeling possible uncertain features. We then propose a two-stage learning algorithm: First, an adaptive stochastic gradient (ASG) algorithm is used to get good estimates for the unknown parameters in the mechanistic component of the hybrid model. Then, the Adam optimizer tunes all parameters to enhance the predictive performance of the entire hybrid model. The asymptotic convergence of the ASG-based adaptive predictor is established without requiring any excitation data conditions, thereby providing a good initial parameter estimate for prediction. Based on this, the fast-converging Adam optimizer further refines the parameters to enhance overall prediction accuracy. Experiments on a real-world dataset of intentional injury cases in China show that our new hybrid model combined with our two-stage ASG-Adam algorithm, outperforms the existing related methods in sentencing prediction performance, including those based on neural networks and saturated mechanism models.

Moral judgment is an integral part of judicial adjudication. If courts disregard the moral concerns of the public, their judgments can easily spark moral controversy. This article examines the moral considerations underlying judicial adjudication, analyzing the moral pressures on justice, the ways justice responds, and the boundaries between moral considerations and legal rules. In China, moral disputes are particularly pronounced in cases involving justifiable self-defense. This article conducts a quasinatural experiment using such cases as samples. The findings are as follows: First, there is a phenomenon known as the “result-only theory” in the trials of justifiable self-defense in China, which significantly contributes to the controversy in these cases. Second, in response to the moral pressures surrounding self-defense, the judiciary has begun to address moral claims, often employing a consequentialist approach. Third, while legal rules fundamentally determine the nature of legal reasoning in justifiable self-defense trials, moral considerations mainly guide the severity of the sentencing outcomes. Additionally, we must be aware of the potential risks associated with judicial responses to moral demands and seek ways to mediate these risks throughout the process.

Model merging has become a popular approach for combining individual models into a single model that inherits their capabilities and achieves improved performance. However, its success has not yet been transferred to semantic segmentation tasks due to two major challenges: 1) current model merging methods predominantly employ static merging strategies with fixed coefficients, limiting their ability to incorporate task-specific prior knowledge and 2) semantic segmentation faces large distribution shifts across multiple domains, causing negative transfer in the merged model. In this article, we propose an effective model merging approach for semantic segmentation, named M2Seg. To dramatically integrate relevant priors based on the input data, we propose a novel SVD-structured MoE module for adaptive merging. To address the severe distribution shifts, we further introduce a test-time dynamic calibration function designed to minimize discrepancies between training and test statistics. Additionally, historical information is leveraged to refine activation statistics during inference. Recognizing that unreliable data can negatively impact update directions, we develop a pixel-efficient entropy minimization mechanism to filter unstable pixels, thus stabilizing the merging process and enhancing segmentation performance. Extensive experiments on both seen and unseen semantic segmentation tasks demonstrate the superior effectiveness and generalization capability of our proposed method. The source code and pretrained checkpoints are available athttps://github.com/cht619/MMSeg

Probation is a crucial institution in modern criminal law, embodying the principles of fairness and justice while contributing to the harmonious development of society. Despite its importance, the current Intelligent Judicial Assistant System (IJAS) lacks dedicated methods for probation prediction, and research on the underlying factors influencing probation eligibility remains limited. In addition, probation eligibility requires a comprehensive analysis of both criminal circumstances and remorse. Much of the existing research in IJAS relies primarily on data-driven methodologies, which often overlooks the legal logic underpinning judicial decision-making. To address this gap, we propose a novel approach that integrates legal logic into deep learning models for probation prediction, implemented in three distinct stages. First, we construct a specialized probation dataset that includes fact descriptions and probation legal elements (PLEs). Second, we design a distinct probation prediction model named the Multi-Task Dual-Theory Probation Prediction Model (MT-DT), which is grounded in the legal logic of probation and the Dual-Track Theory of Punishment. Finally, our experiments on the probation dataset demonstrate that the MT-DT model outperforms baseline models, and an analysis of the underlying legal logic further validates the effectiveness of the proposed approach.