大语言模型(Large Language Models,LLMs)目前正在重塑各行各业的学习方式、思维模式和研究范式。如何使LLMs与行业结合、重构LLMs与行业的关系,是推动企业数字化变革和社会发展的重要命题。要实现LLMs在垂域发挥重要作用,最重要的是提...大语言模型(Large Language Models,LLMs)目前正在重塑各行各业的学习方式、思维模式和研究范式。如何使LLMs与行业结合、重构LLMs与行业的关系,是推动企业数字化变革和社会发展的重要命题。要实现LLMs在垂域发挥重要作用,最重要的是提升LLMs的推理能力。本文以如何提升LLMs在会计领域的推理能力为起点,提出会计垂域推理能力的概念、研究路径、评测标准,分析中文开源模型清华智谱的GLM系列的评测结果,为后续的推理研究提供标准范式,并为如何提升会计推理能力提供评价标准,力图推动LLMs在会计领域达到应有水平。同时,为验证LLMs的会计推理能力,本文比较了GLM-6B、GLM-130B、GLM-4在算术推理能力和会计常识推理能力方面的差别,并将OPENAI的GPT-4作为基准进行分析。结果表明,在不同推理提示工程下,模型规模显著影响推理能力,虽然各种模型算术推理能力已经得到极大的提高,但是会计推理能力还远不能达到应用水平,需要在应用中逐层优化,研究为LLMs会计垂域进入应用实践的优化过程提供参考。展开更多
Machine-learning methodologies have increasingly been embraced in landslide susceptibility assessment.However,the considerable time and financial burdens of landslide inventories often result in persistent data scarci...Machine-learning methodologies have increasingly been embraced in landslide susceptibility assessment.However,the considerable time and financial burdens of landslide inventories often result in persistent data scarcity,which frequently impedes the generation of accurate and informative landslide susceptibility maps.Addressing this challenge,this study compiled a nationwide dataset and developed a transfer learning-based model to evaluate landslide susceptibility in the Chongqing region specifically.Notably,the proposed model,calibrated with the warmup-cosine annealing(WCA)learning rate strategy,demonstrated remarkable predictive capabilities,particularly in scenarios marked by data limitations and when training data were normalized using parameters from the source region.This is evidenced by the area under the receiver operating characteristic curve(AUC)values,which exhibited significant improvements of 51.00%,24.40%and 2.15%,respectively,compared to a deep learning model,in contexts where only 1%,5%and 10%of data from the target region were used for retraining.Simultaneously,there were reductions in loss of 16.12%,27.61%and 15.44%,respectively,in these instances.展开更多
文摘大语言模型(Large Language Models,LLMs)目前正在重塑各行各业的学习方式、思维模式和研究范式。如何使LLMs与行业结合、重构LLMs与行业的关系,是推动企业数字化变革和社会发展的重要命题。要实现LLMs在垂域发挥重要作用,最重要的是提升LLMs的推理能力。本文以如何提升LLMs在会计领域的推理能力为起点,提出会计垂域推理能力的概念、研究路径、评测标准,分析中文开源模型清华智谱的GLM系列的评测结果,为后续的推理研究提供标准范式,并为如何提升会计推理能力提供评价标准,力图推动LLMs在会计领域达到应有水平。同时,为验证LLMs的会计推理能力,本文比较了GLM-6B、GLM-130B、GLM-4在算术推理能力和会计常识推理能力方面的差别,并将OPENAI的GPT-4作为基准进行分析。结果表明,在不同推理提示工程下,模型规模显著影响推理能力,虽然各种模型算术推理能力已经得到极大的提高,但是会计推理能力还远不能达到应用水平,需要在应用中逐层优化,研究为LLMs会计垂域进入应用实践的优化过程提供参考。
基金Project(2301DH09002)supported by the Bureau of Planning and Natural Resources,Chongqing,ChinaProject(2022T3051)supported by the Science and Technology Service Network Initiative,ChinaProject(2018-ZL-01)supported by the Sichuan Transportation Science and Technology,China。
文摘Machine-learning methodologies have increasingly been embraced in landslide susceptibility assessment.However,the considerable time and financial burdens of landslide inventories often result in persistent data scarcity,which frequently impedes the generation of accurate and informative landslide susceptibility maps.Addressing this challenge,this study compiled a nationwide dataset and developed a transfer learning-based model to evaluate landslide susceptibility in the Chongqing region specifically.Notably,the proposed model,calibrated with the warmup-cosine annealing(WCA)learning rate strategy,demonstrated remarkable predictive capabilities,particularly in scenarios marked by data limitations and when training data were normalized using parameters from the source region.This is evidenced by the area under the receiver operating characteristic curve(AUC)values,which exhibited significant improvements of 51.00%,24.40%and 2.15%,respectively,compared to a deep learning model,in contexts where only 1%,5%and 10%of data from the target region were used for retraining.Simultaneously,there were reductions in loss of 16.12%,27.61%and 15.44%,respectively,in these instances.
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.60505008, No.60603086)国家自然科学基金优秀国家重点实验室专项基金资助项目 (the Key Program of the National Natural Science Foundation of P.R. China under Grant No.60723003)江苏省自然科学基金(the Natural Science Foundation of Jiangsu Province of China under Grant No.BK2007520)
