• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    中

    中国政法大学

    China University of Political Science and Law
    院校EST. 1952
    3.6万论文总数
    13.3万引用总数

    论文量&引用量时间轴

    机构学者

    论文(10000)

    年份
    起
    –
    止
    排序
    1Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
    Wenhan Yu,Xinbo Lin, Lanxin Ni, Jinhua Cheng,Lei Sha

    Existing legal benchmarks for Large Language Models (LLMs) primarily focus on final judgment outcomes or isolated subtasks, making it difficult to systematically evaluate the multi-step reasoning processes and reasoning quality required in real-world legal decision-making. To address this gap, we introduce MSLR, a Chinese benchmark for multi-step legal reasoning, which models and evaluates complete judicial reasoning trajectories based on the IRAC (Issue-Rule-Application-Conclusion) framework. MSLR comprises 1389 Chinese insider trading judgments issued between 2005 and 2024, with approximately 60,000 step-level reasoning paths annotated through a combination of human and automated methods, averaging 43 intermediate reasoning steps per case. Based on MSLR, we adopt two evaluation metrics, IRAC Recall and LLM Score, to provide a fine-grained assessment of legal reasoning capabilities. We systematically evaluate 19 mainstream general-purpose, legal-domain, and reasoning-oriented models. The results show that current models exhibit overall limited performance on multi-step legal reasoning tasks; even the best-performing o1-mini model fails to exceed 75% IRAC Recall. In addition, we report the performance of mainstream models on structured annotation tasks and legal judgment reasoning tasks. The MSLR dataset and benchmark construction code are publicly available at https://github.com/yuwenhan07/MSLR-Bench.

    2027INFORMATION PROCESSING & MANAGEMENT(2027)引用:5
    引用
    AI阅读
    加入学术空间
    2Always On, Undermining at Home? Spillover and Crossover Effects of Workplace Telepressure after Hours on Family Undermining and Spouse’s Well-Being
    Xiaoyan He, Ya Cao, Qin Gao, Zenan Zhang,Ran Bian, Xiao-Hua Frank Wang

    Drawing on the spillover-crossover model, we investigate how workplace telepressure after hours (WTA) influences employees’ behaviors at home and crosses over to affect their spouses’ well-being, including relationship satisfaction and family emotional exhaustion. We suggest that work-related rumination serves as a key mechanism, and that core self-evaluations (CSE) moderate these effects. Using a three-wave, multisource design with 227 dual-earner couples, we found that WTA was indirectly and negatively linked to family undermining through problem-solving pondering, which in turn improved spouses’ relationship satisfaction and decreased their family emotional exhaustion. This positive spillover-crossover effect was only present among employees with high CSE. Conversely, WTA was indirectly and positively associated with family undermining through affective rumination, which then lowered spouses’ relationship satisfaction and increased their family emotional exhaustion. This negative spillover-crossover effect was not significant when employees had high CSE. Overall, this study reveals new insights into how telepressure affects both employees and their spouses, emphasizing the crucial role of personal resources in managing spillover and crossover effects of telepressure.

    2026Current Psychology(2026)引用:89
    引用
    AI阅读
    加入学术空间
    3LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
    Haitao Li, Yifan Chen, Shuo Miao,Qian Dong,Jia Chen,Yiran Hu,Junjie Chen, Minghao Qin,Yueyue Wu,Yujia Zhou,Qingyao Ai,Yiqun Liu,

    While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.

    2026CoRR(2026)引用:11
    引用
    AI阅读
    加入学术空间
    4Simulating Dispute Mediation with LLM-Based Agents for Legal Research
    Junjie Chen,Haitao Li, Minghao Qin,Yujia Zhou, Yanxue Ren, Wuyue Wang,Yiqun Liu,Yueyue Wu,Qingyao Ai

    Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.

    2026AAAI 2026(2026)引用:8
    引用
    AI阅读
    加入学术空间
    5SCGRN: Spatiotemporal Causal Graph Reasoning Network for Regional Economic Development Modeling
    Libin Zhou, Mingsen Wang, Qizhen Chen, Hongfeng Han

    High-quality economic development calls for data-driven, interpretable modeling to support regional policy decisions. However, existing forecasting methods struggle with causal reasoning and spatiotemporal integration. Traditional econometric models capture structural relationships but often miss complex nonlinear patterns, while recent machine learning models (e.g., deep neural networks) achieve accuracy at the cost of interpretability. In particular, current spatiotemporal graph neural networks (ST-GNNs) assume fixed or learned correlations but lack explicit causal modeling and struggle to jointly capture spatial spillovers and temporal dynamics. To address these gaps, we propose a Spatiotemporal Causal Graph Reasoning Network (SCGRN) that integrates causal discovery, spatial graph learning, temporal sequence modeling, and counterfactual policy simulation. SCGRN first uncovers a directed acyclic causal graph of key economic factors, then embeds regions in a spatial graph neural network, and finally models temporal dynamics with recurrent units-all guided by the causal graph. Experiments on a 21-year panel dataset covering 31 Chinese provincial-level regions (651 province-year observations) demonstrate a 12.3% reduction in RMSE over state-of-the-art baselines, and SCGRN recovers economically plausible directed relations consistent with prior evidence. Moreover, SCGRN supports policy scenario analysis: by simulating interventions, it generates interpretable counterfactual outcomes for decision-makers. This work provides a novel interpretable AI approach for regional economic development modeling, with practical potential for evidence-based policy and resource allocation.

    2026INFORMATION PROCESSING & MANAGEMENT(2026)引用:4
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 10000 篇论文

    合作机构(100)

    中国人民大学合作论文 239
    北京大学合作论文 184
    清华大学合作论文 133
    北京师范大学合作论文 133
    中国社会科学院合作论文 99
    中国人民公安大学合作论文 89
    中国科学院合作论文 49
    华中科技大学合作论文 49
    中央财经大学合作论文 47
    中央民族大学合作论文 44

    机构统计