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.

A criminal judicial opinion represents the judge's disposition of a case, including the decision rationale and sentencing.Automatically generating such opinions can assist in analyzing sentencing consistency and provide judges with references to past similar cases.However, current research typically approaches this task by dividing it into two isolated subtasks: legal reasoning and sentencing prediction.This separation often leads to inconsistency between the reasoning and predictions, failing to meet real-world judicial requirements.Furthermore, prior studies rely on manually creating knowledge to enhance applicability, yet such methods remain limited in practical deployment.To address these limitations and better align with legal practice, we propose a new LegalAI task: Criminal Judicial Opinion Generation, which simultaneously produces both legal reasoning and sentencing decisions.To achieve this, we introduce the LegalChainReasoner framework that applies structured legal chains to guide the model through comprehensive case assessments.By integrating factual premises, composite legal conditions, and sentencing conclusions, our approach ensures flexible knowledge injection and end-to-end opinion generation.Experiments on real-world, open-source Chinese legal case datasets demonstrate that our method outperforms baseline models. 1

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.

Analogical reasoning over Multimodal Knowledge Graphs (MMKGs) couples abductive relation induction with inductive tail completion. However, existing approaches rely on static fusion mechanisms that overlook the inherent asymmetry of modal relevance: while visual cues elucidate concrete entities, they are often noisy or irrelevant for abstract concepts, where text and graph structure provide decisive signals. Furthermore, prior methods fail to enforce consistency between induced relations and the modality patterns implied by the analogical context. To bridge this gap, we introduce RMAR, a Relation-aware Multimodal Analogical Reasoning framework with two complementary paths. An explicit path estimates modality fingerprints to score compatibility during relation induction and guide fusion during tail completion. An implicit path employs adaptive gating to blend structural, textual, and visual signals conditioned on the specific query context. To address the limitations of current benchmarks, which overrepresent concrete entities, we release MCNetAnalogy, and its companion graph, MCNetKG, a rigorous dataset enriched with abstract concepts and actions. RMAR is backbone-agnostic and works with multimodal knowledge graph embedding (MKGE) and transformer-based (MPT) pipelines. Extensive experiments demonstrate that RMAR delivers consistent gains across both embedding-based and transformer-based backbones, achieving a 29% relative improvement on MCNetAnalogy. Ablation studies confirm that RMAR's relation-aware modulation is particularly effective when modal evidence is weak or ambiguous.

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.

Trajectory anomaly detection is critical in trajectory data mining. The objective is to identify abnormal movements of objects. Most existing trajectory anomaly detection methods focus on determining whether an entire trajectory is anomalous, lacking the ability to identify the exact anomalous sub-trajectories. Although recent research has started addressing anomalous sub-trajectories detection, these methods fail to extract the specific route pattern for the target trajectory. As a result, they struggle to identify anomalous sub-trajectories when the same sub-trajectory is regarded as normal in other routes. To overcome these limitations, we propose a Route-Enhanced Conditional Anomalous Sub-Trajectory detection model (RECAST). RECAST has two innovative components: (1) a Route Discovery Network (RDN) that extracts the normal route pattern of the given trajectory; (2) a Conditional Anomalous Sub-trajectory Detection (CASD) network that detects anomalies conditioned on the estimated route patterns. Our design enables RECAST to identify sub-trajectories as anomalous even if they are normal in other routes, as long as they are unlikely to occur in the route of the given trajectory. We evaluate the effectiveness and efficiency of RECAST using two real-world datasets. The results demonstrate that our method outperforms the state-of-the-art methods in detection accuracy with competitive runtime efficiency1.

Judgment summaries are beneficial for legal practitioners to comprehend and retrieve case law efficiently. Unlike summaries in general domains, e.g., news, judgment summaries often require a clear structure. Such a structure helps readers grasp the information contained in the summary and reduces information loss. To the best of our knowledge, none of the existing text summarizers can generate summaries aligned with the summary structure in the legal domain. Inspired by this observation, this paper introduces a Summary Structure-Enhanced (SSE) method to synthesize structured summaries for legal documents. SSE can easily be incorporated into the Encoder-Decoder framework, which is commonly adopted in state-of-the-art text summarizers. Experiments on the datasets of New Zealand and Chinese judgments show that the proposed method consistently improves the performance of state-of-the-art summarizers in terms of Rouge scores.

Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech consists of content and speaker style information and aims to untangle them to change the style information for conversion. Previous works focus on reducing the dimension of speech to get the content information. But the size is hard to determine to lead to the untangle overlapping problem. We propose the Disentangled Representation Voice Conversion (DRVC) model to address the issue. DRVC model is an end-to-end self-supervised model consisting of the content encoder, timbre encoder, and generator. Instead of the previous work for reducing speech size to get content, we propose a cycle for restricting the disentanglement by the Cycle Reconstruct Loss and Same Loss. The experiments show there is an improvement for converted speech on quality and voice similarity.