China launches first supervisory and disciplinary inspection large model Qingjian

The wave of digital transformation has brought a "smart brain" to disciplinary inspection and supervision. On April 21, the first large model tailored for this field in China, named "Qingjian" and developed by Southeast University, was officially launched. This milestone represents a deep integration of cutting-edge AI with national strategic priorities, offering strong technical support for the professionalization and intelligent upgrade of disciplinary inspection and supervision.
Interdisciplinary Collaboration Yields Smart Tools
The Qingjian model is not the work of a single discipline; it stems from deep interdisciplinary collaboration. It was jointly developed by the Institute of Disciplinary Inspection and Supervision and the School of Law at Southeast University, along with the Key Laboratory of New Generation Artificial Intelligence Technology and Interdisciplinary Application, and the Laboratory of Future Law and Digital Intelligence Innovation. This cross-disciplinary research approach ensures a solid legal foundation while enabling the model to leverage the most advanced AI algorithms.
Five Core Functions Boost Operational Efficiency
According to the development team, Qingjian offers five core application scenarios: authoritative policy interpretation, analysis of integrity risks in typical cases, customized integrity education, academic research data support, and intelligent Q&A for routine business operations. In daily office work, it helps staff intelligently draft reports, review the integrity of evidence chains, and automatically recommend applicable legal provisions—greatly improving the standardization and efficiency of disciplinary inspection and supervision practices.
A Precisely Adapted, Secure Technical Foundation
To ensure professionalism and reliability, Qingjian integrates a vast amount of internal party regulations, national laws, academic research, and practical case studies. Notably, the model has meticulously annotated local normative documents from all 31 provinces, allowing it to flexibly adapt to regional differences in disciplinary and law enforcement.
On the technical side, the team adopted a full-process approach that combines on-premises deployment with retrieval-augmented generation, and built a multi-dimensional rule validator that checks for legal provision accuracy and logical consistency. This design ensures data security and compliance while enabling the model to produce clear, rigorous, and logically consistent reasoning chains when handling complex case determinations.
Related article
U.S. Stocks Hit Historic Milestone as AI and Aerospace Giants Prepare for Trillion-Dollar Debut
Elon Musk, Sam Altman, and Dario Amodei, three titans of the technology sector, are advancing toward initial public offerings for their respective ventures. With SpaceX, OpenAI, and Anthropic—three industry behemoths nearing trillion-dollar valuation
Swedish AI Startup Lovable Eyes $13.2 Billion Valuation After Major Funding Round
As AI-driven coding tools gain traction, Swedish startup Lovable has secured a major funding round. The company aims to raise $3 billion, potentially boosting its valuation to $13.2 billion—double the $6.6 billion recorded last December. Menlo Ventur
Google Tests Remy AI Agent for Gemini as Focus Shifts to User Control
According to Business Insider, Google is testing Remy, a new AI personal agent for Gemini. This tool aims to execute tasks on behalf of users, streamlining both professional workflows and daily routines.Currently, Remy is undergoing testing in an int
Related Special Topic Recommendations
Comments (1)
0/500

The wave of digital transformation has brought a "smart brain" to disciplinary inspection and supervision. On April 21, the first large model tailored for this field in China, named "Qingjian" and developed by Southeast University, was officially launched. This milestone represents a deep integration of cutting-edge AI with national strategic priorities, offering strong technical support for the professionalization and intelligent upgrade of disciplinary inspection and supervision.
Interdisciplinary Collaboration Yields Smart Tools
The Qingjian model is not the work of a single discipline; it stems from deep interdisciplinary collaboration. It was jointly developed by the Institute of Disciplinary Inspection and Supervision and the School of Law at Southeast University, along with the Key Laboratory of New Generation Artificial Intelligence Technology and Interdisciplinary Application, and the Laboratory of Future Law and Digital Intelligence Innovation. This cross-disciplinary research approach ensures a solid legal foundation while enabling the model to leverage the most advanced AI algorithms.
Five Core Functions Boost Operational Efficiency
According to the development team, Qingjian offers five core application scenarios: authoritative policy interpretation, analysis of integrity risks in typical cases, customized integrity education, academic research data support, and intelligent Q&A for routine business operations. In daily office work, it helps staff intelligently draft reports, review the integrity of evidence chains, and automatically recommend applicable legal provisions—greatly improving the standardization and efficiency of disciplinary inspection and supervision practices.
A Precisely Adapted, Secure Technical Foundation
To ensure professionalism and reliability, Qingjian integrates a vast amount of internal party regulations, national laws, academic research, and practical case studies. Notably, the model has meticulously annotated local normative documents from all 31 provinces, allowing it to flexibly adapt to regional differences in disciplinary and law enforcement.
On the technical side, the team adopted a full-process approach that combines on-premises deployment with retrieval-augmented generation, and built a multi-dimensional rule validator that checks for legal provision accuracy and logical consistency. This design ensures data security and compliance while enabling the model to produce clear, rigorous, and logically consistent reasoning chains when handling complex case determinations.
U.S. Stocks Hit Historic Milestone as AI and Aerospace Giants Prepare for Trillion-Dollar Debut
Elon Musk, Sam Altman, and Dario Amodei, three titans of the technology sector, are advancing toward initial public offerings for their respective ventures. With SpaceX, OpenAI, and Anthropic—three industry behemoths nearing trillion-dollar valuation
Swedish AI Startup Lovable Eyes $13.2 Billion Valuation After Major Funding Round
As AI-driven coding tools gain traction, Swedish startup Lovable has secured a major funding round. The company aims to raise $3 billion, potentially boosting its valuation to $13.2 billion—double the $6.6 billion recorded last December. Menlo Ventur





Home






