Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

Soil secondary salinization is one of the typical ecological side effects caused by land and water resources development in northwestern arid China. Factors that affect the occurrences and developments of salinization come from both natural conditions and human activities. Research on the mechanisms of salinization, build dynamic prediction model of salt accumulation and analyze sensitivities to different factors would supply effective references to the prediction and prevention of soil salinization. It is well known that related factors are always intertexture together, affecting each other, which result in multivariable, nonlinear and overall influences that work on the process of soil salinization. Artificial intelligence technologies may play important role in this domain. In this paper, genetic artificial neural network based model is built to simulate and evaluate soil salt accumulation and sensitivity of soil salinization. Example is taken from the Shule River watershed, typical arid area in northwestern China. Basic data of June 2000 are prepared depending on GIS and Remote Sensing. Precipitations, evaporations, groundwater levels, groundwater chemical analysis data and soil accumulation data are achieved and interpolated in the research area. Slope of the land are derived from DEM, MODIS images are used in the process of dealing with land use information. At the same time, landform and soil type are considered in model building. Soil salt accumulation is analyzed with its 8 influenced factors with verified models. Results showing that groundwater TDS is the most sensitive factor followed by groundwater level, evaporation and the depth of upper bed of clay. In most cases clay layers play key roles in soil salt accumulation, precipitation and slop have similar sensitivities. Results would have better research and application value in arid areas of northwestern China.