Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen, Guozhou Zheng, Huajun Chen, Shumin Deng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Kehua Feng, Keyan Ding, Tan Hongzhi, Kede Ma, Zhihua Wang, Shuangquan Guo, Cheng Yuzhou, Ge Sun, Guozhou Zheng, Qiang Zhang, Huajun Chen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored. To address this gap, we propose complexity-impacted reasoning score CIRS, which combines structural and logical attributes, to measure the correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity by considering the difficulty and the cyclomatic complexity. Through an empirical analysis, we find not all code data of complexity can be learned or understood by LLMs. Optimal level of complexity is critical to the improvement of reasoning abilities by program-aided prompting. Then we design an auto-synthesizing and stratifying algorithm, and apply it to instruction generation for mathematical reasoning and code data filtering for code generation tasks. Extensive results demonstrates the effectiveness of our proposed approach.

Zhen Bi, Ningyu Zhang, Yida Xue, Yixin Ou, Daxiong Ji, Guozhou Zheng, Huajun Chen. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Recent years, the scale of spatial data is developing more and more huge and its storage has encountered a lot of problems. Traditional DBMS can efficiently handle some big spatial data. However, popular open source relational database systems are overwhelmed by the high insertion rates, querying requirements and terabytes of data that these systems can handle. On the other hand, key-value storage can effectively support large scale operations. To resolve the problems of big vector spatial data's storage and query, we bring forward HBase Spatial, a scalable spatial dada storage based on HBase. At first, we analyze the distributed storage model of HBase. Then, we design a distributed storage and index model. Finally, the advantages of our storage model and index algorithm are proven by experiments with both big sample sets and typical benchmarks on cluster compared with MongoDB and Mysql, which shows that our model can effectively enhance the query speed of big spatial data and provide a good solution for storage.

Chaos of data is the total unpredictability of all the data elements, and can by quantified by Shannon entropy. In this paper, we firstly propose an entropy based theoretic framework for machine learning, which states that chaos in sample data will decrease and rule will advance as learning progresses. However, it is usually time consuming to apply the theoretic framework because groups of rule need to be trained iteratively and data chaos will be recalculated during each iteration. To implement the theoretic framework for scalable learning, we propose a MapReduce based distributed computational framework. In a case study of classification, the framework parallelly trains multiple classifiers and calculats chaos of the sample set during each iteration, and then resamples a small sample subset with the highest entropy for training of the next iteration, reducing chaos in sample data as quickly as possible. With typical classification benchmarks, our experiment presents entropy in sample data, and proves that the theoretic framework is rational and can help improve the accuracy of machine learning. Meanwhile, the computational framework shows high performance including high efficiency and scalability for large scale learning on hadoop cluster.

Abstract In the presence of a Database Grid where a huge number of highly diverse, widely distributed, autonomously managed databases can be involved in a sharing cycle, database tools and middleware should be well suited for schema mediation and query processing in a semantically meaningful way. In this paper, an implemented system called DartGrid is presented. DartGrid is intended to provide a semantic infrastructure for building database grid applications. We explore the essential and fundamental roles played by Resource Description Framework (RDF) semantics for database grids and implement a set of semantically enabled tools and grid services such as semantic browser, semantic mapping tools, ontology service, semantic query service and semantic registration service. We propose an RDF‐View‐based approach for relational schema mediation and describe the view‐based semantic query rewriting algorithm implemented in DartGrid. DartGrid has been used to build a real database grid application for Traditional Chinese Medicine in China. Copyright © 2006 John Wiley & Sons, Ltd.

The negotiation process is a necessary precondition for many wide-area based applications which involve interactions across multiple autonomous entities. In the case where database resources are explicitly exposed to the distributed computing context like the Grid, it is necessary for unauthorized database users to get authorized so that they can be granted with certain privileges to access the desirable database resources. The facility to establish a legal identity for database user is one of the functionalities that the database resource management framework should provide. In this paper, we give a handshaking protocol which is applied between database clients and database service providers to achieve the database-specific negotiation. It's a six-phased protocol, which is described in terms of service operations in our database resource management middleware, which is an OGSA compliant service-based system.