Large Language Models (LLMs) are widely used in legal judgment prediction tasks, which aim to enhance judicial efficiency. However, the length of legal fact descriptions poses a significant challenge to the application of LLMs. Long inputs not only introduce noise, affecting output quality, but also increase processing time. While existing text compression methods, such as generating summaries or training models to implicitly reduce text dimensionality, can shorten input length, they often face the slow generation speeds and limited interpretability issues. To address these issues and inspired by information bottleneck-based text compression, we propose the Zipped Information Processor for Legal Judgment Prediction method, ZipLJP. By effectively integrating legal knowledge into the compression process, ZipLJP not only reduces input length but also improves processing efficiency and prediction quality. Experiments show that our approach achieves better performance compared to the previous methods on two widely used open-source and real-world datasets.

Senbo Zhang, Qiqi Wang, Fanghao Lou, Guanyu Chen, Yihong Pan, Huijia Li, Qian Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models (LLMs) are playing an increasingly pivotal role in LegalAI.However, existing benchmarks are primarily tailored for legal professionals, emphasizing deep reasoning and explainability.While public-facing legal applications demand outputs that are direct, actionable, and accessible, a need largely overlooked by current evaluation frameworks.To bridge this gap, we propose a public-oriented LegalAI benchmark grounded in legal functionalism and genre analysis.Specifically, we categorize public legal demands into two core tasks: Instant Question Answering and Legal Text Generation.We further introduce three public-oriented evaluation dimensions: legal normativity, content relevance, and format usability, which collectively assess the practical validity and user readiness of model outputs.To reflect real-world lay user usage, we evaluate 17 LLMs on Pub-LawBench using only simple prompts and Chain-of-Thought under a vanilla inference setting, excluding complex techniques like RAG or agent-based methods inaccessible to non-experts.Experiments reveal limitations of current LLMs in delivering effective public-oriented legal assistance, highlighting the need for more user-centric model development and benchmarking.1 * Equal contribution.Tasks & Metrics COLIEE CaseHOLD CUAD LeCaRD LexGLUE LegalBench LegalEval LawBench KoBLEX GreekBar SwissJudg Pub-LawBench Part I: Task Scenarios Legal Concept Interp.

Urban spatial tasks span multiple levels, ranging from area-level analysis, crime prediction, and taxi demand forecasting to POI-level tasks such as new store recommendation. Urban knowledge graphs (UrbanKGs) can enhance these tasks by integrating structured urban knowledge. However, existing studies face two main issues: most research uses task-specific UrbanKGs for corresponding single-level predictions, and public UrbanKGs contain only coarse-grained administrative areas, lacking the rich semantic and spatial relationships required for multi-level tasks. We propose a Hierarchically Structured UrbanKG Dataset (HUSK) with an intermediate functional zone layer that bridges and enriches the understanding across multiple levels, and evaluate it on three area-level and three POI-level tasks, showing accuracy improvements over single-view baselines.

Overlapping graph clustering is essential to understand the nature and behavior of real complex systems including human interactions, technical systems and transportation network. However, in addition of topological structure, many real-world networked systems contain spare factors, i.e., attributes of networks. Despite the considerable efforts that have been made in graph clustering, they only concentrate on the topological structure, which lack a profound understanding of cluster configuration on attributed graphs. To address this great challenge, in this article, we propose a new overlapping graph clustering algorithm by integrating the topological and attributive information into a cluster potential game (CPG). Firstly, a generalized definition of the utility function is provided, which measures the payoff of each node based on different node-to-cluster distance functions. It is worth mentioning that the model we proposed is able to associate with the classic ordinal potential game well. Then, we define the measures of both tightness and the homogeneity in each cluster, and introduce a novel two-way selection mechanism. The goal is to extend the flexibility of the cluster potential game, so that one can achieve a win-win situation between nodes and clusters. Finally, a distributed and heterogeneous multiagent system (DHMAS) is carefully designed based on a fast self-learning algorithm (SLA) for attributed overlapping graph clustering. Two series of experiments are implemented in multi-types datasets and the results verify the effectiveness and the scalability after the comparison with the most advanced approaches of literature.

Graph clustering is essential to understand the nature and behavior of real world such as social network, technical network and transportation network. Different from the existing studies, we propose a new Markov clustering method inspired by belief dynamical system which can be used in general for optimization of different quality measures. By a rigorous theoretical proof, it has been shown that the quality function's global maximum is a dynamical system's asymptotically stable fixed point. Under specified conditions, the trajectory of the dynamical converges to the cluster labels of corresponding nodes. Particularly, a general formulation can unite well-known methodologies and the quality functions that correspond to them. The algorithm is fast and its computational complexity is nearly linear with the scale of sparse networks. Finally, we thoroughly evaluate our methodology on a variety of synthetic and real-world networks with various network properties, particularly on the dynamical networks. The results demonstrate that when compared to the current state-of-the-art algorithms, our method performs better on these networks.

Graph clustering is one of the most significant, challenging, and valuable topic in the analysis of real complex networks. To detect the cluster configuration accurately and efficiently, we propose a new Markov clustering algorithm based on the limit state of the belief dynamics model. First, we present a new belief dynamics model, which focuses beliefs of multicontent and randomly broadcasting information. A strict proof is provided for the convergence of nodes' normalized beliefs in complex networks. Second, we introduce a new Markov clustering algorithm (denoted as BMCL) by employing a belief dynamics model, which guarantees the ideal cluster configuration. Following the trajectory of the belief convergence, each node is mapped into the corresponding cluster repeatedly. The proposed BMCL algorithm is highly efficient: the convergence speed of the proposed algorithm researches O(TN) in sparse networks. Last, we implement several experiments to evaluate the performance of the proposed methods.

Vulnerability assessment—a critical issue for networks—attempts to foresee unexpected destructive events or hostile attacks in the whole system. In this article, we consider a new Markov global connectivity metric—Kemeny constant, and take its derivative called Markov criticality to identify critical links. Markov criticality allows us to find links that are most influential on the derivative of Kemeny constant. Thus, we can utilize it to identity a critical link ( i , j ) from node i to node j , such that removing it leads to a minimization of networks’ global connectivity, i.e., the Kemeny constant. Furthermore, we also define a novel vulnerability index to measure the average speed by which we can disconnect a specified ratio of links with network decomposition. Our method is of high efficiency, which can be easily employed to calculate the Markov criticality in real-life networks. Comprehensive experiments on several synthetic and real-life networks have demonstrated our method’s better performance by comparing it with state-of-the-art baseline approaches.

The design of fusion engines is a subject of great importance in a variety of fields. In this paper, we focus on the problem of linear fusion at the feature level for multiple signal matrices with noises, with the features being extremal eigenvectors. When given multiple similarity matrices, the objective is to find an estimate of the latent signal eigenspace. The concentration result for the inner product of features from different matrix samples is developed, utilizing the random matrix theory. Based on of the theoretical results, we proposed an efficient algorithm,EigFuse, to solve the constrained data-driven optimization problem with different level of noises. Our method is of high efficiency by comparing it with state-of-the-art baseline approaches with multiple noise levels. Comprehensive experiments on several synthetic as well as real-life networks demonstrate our method’s superior performance.

In many electronic commerce systems, detecting significant clusters is of great value to the analysis, design, and optimization of the commerce behaviors. In this article, we propose a new dynamical approach to detect the cluster configuration fast and accurately which can be applied to electronic commerce systems. First, we analyze the two-stage game in which the leader group members make contributions prior to the follower group, and propose an exact index, i.e., the leadership, to characterize the key leaders. Then an efficient dynamical system is used to guarantee the cluster configuration converges to an optimal state, which assigns each node to the corresponding cluster based on quality optimization, repeatedly. Our method is of high efficiency-the exponential term in the proposed dynamical system makes the convergence to be very fast with a nearly linear time. Extensive experiments on multiple types of datesets demonstrate the state-of-the-art performance of proposed method.

With the explosion of social media networks, many modern applications are concerning about people's connections, which leads to the so-called social computing. An elusive question is to study how opinion communities form and evolve in real-world networks with great individual diversity and complex human connections. In this scenario, the classic K-means technique and its extended versions could not be directly applied, as they largely ignore the relationship among interactive objects. On the other side, traditional community detection approaches in statistical physics would be neither adequate nor fair: they only consider the network topological structure but ignore the heterogeneous-objects' attributive information. To this end, we attempt to model a realistic social media network as a discrete-time dynamical system, where the opinion matrix and the community structure could mutually affect each other. In this paper, community detection in social media networks is naturally formulated as a multi-objective optimization problem (MOOP), i.e., finding a set of densely connected components with similar opinion vectors. We propose a novel and powerful graph K-means framework, which is composed of three coupled phases in each discrete-time period. Specifically, the first phase uses a fast heuristic approach to identify those opinion leaders who have relatively high local reputation; the second phase adopts a novel dynamic game model to find the locally Pareto-optimal community structure; and the final phase employs a robust opinion dynamics model to simulate the evolution of the opinion matrix. We conduct a series of comprehensive experiments on real-world benchmark networks to validate the performance of GK-means through comparisons with the state-of-the-art graph clustering technologies.

Besides the topological structure, there are additional information, i.e., node attributes, on top of the plain graphs. Usually, these systems can be well modeled by attributed graphs, where nodes represent component actors, a set of attributes describe users' portraits and edges indicate their connections. An elusive question associated with attributed graphs is to study how clusters with common internal properties form and evolve in real-world networked systems with great individual diversity, which leads to the so-called problem of attributed graph clustering (AGC). In this paper, we comprehended AGC naturally as a dynamic cluster formation game (DCFG), where each node's feasible action set can be constrained by every cluster in a discrete-time dynamical system. Specifically, we carried out a deep research on a special case of finite dynamic games, named dynamic social game (DSG), the convergence of the finite Nash equilibrium sequence in a DSG was also proved strictly. By carefully defining the feasible action set and the utility function associated with each node, the proposed DCFG can be well related to a DSG; and we showed that a balanced solution of AGC could be found by solving a finite set of coupled static Nash equilibrium problems in the related DCFG. We, finally, proposed a self-learning algorithm, which can start from any arbitrary initial cluster configuration, and, finally, find the corresponding balanced solution of AGC, where all nodes and clusters are satisfied with the final cluster configuration. Extensive experiments were applied on real-world social networks to demonstrate both effectiveness and scalability of the proposed approach by comparing with the state-of-the-art graph clustering methods in the literature.

One of the greatest advancements of the modern era is the evolution of smart grid (SG), which integrates information communication technologies with advanced power electronic technologies to cope with the global energy shortage. The users in SGs are often called the “prosumers,” who not only consume energy but also generate the energy and share it with the utility grid or with other energy consumers. In order to promote sustainable prosumer management in SGs, one of the feasible strategies is to aggregate the prosumers from different locations, but with similar energy behaviors and cohesive interconnections, such groups of prosumers are also called the prosumer-community groups (PCGs). The contribution of this paper is threefold. First, we provide a generalized definition of individual prosumer's energy density, which can be used to detect the underlying leader prosumers in SGs. Second, we formulate the PCG detection (PCG-D) as a multiobjective optimization problem, and present a novel dynamic game model to find the locally Pareto-optimal PCG structure. Third, we propose a partially visible multiagent system (PVMAS), where the viewing angles of both prosumers and PCGs are mutually restricted. The significance of our PVMAS is that it can nicely lead itself to parallelization for PCG-D, due to the fact that the feature updating of each agent is independent of each other. We conduct a series of comprehensive experiments on the simulated SG datasets to validate the performance of PVMAS through comparing it with existing community detection approaches in the literature.

Mining communities or clusters in networks is valuable in analyzing, designing, and optimizing many natural and engineering complex systems, e.g., protein networks, power grid, and transportation systems. Most of the existing techniques view the community mining problem as an optimization problem based on a given quality function(e.g., modularity), however none of them are grounded with a systematic theory to identify the central nodes in the network. Moreover, how to reconcile the mining efficiency and the community quality still remains an open problem. In this paper, we attempt to address the above challenges by introducing a novel algorithm. First, a kernel function with a tunable influence factor is proposed to measure the leadership of each node, those nodes with highest local leadership can be viewed as the candidate central nodes. Then, we use a discrete-time dynamical system to describe the dynamical assignment of community membership; and formulate the serval conditions to guarantee the convergence of each node's dynamic trajectory, by which the hierarchical community structure of the network can be revealed. The proposed dynamical system is independent of the quality function used, so could also be applied in other community mining models. Our algorithm is highly efficient: the computational complexity analysis shows that the execution time is nearly linearly dependent on the number of nodes in sparse networks. We finally give demonstrative applications of the algorithm to a set of synthetic benchmark networks and also real-world networks to verify the algorithmic performance.