TACOMORE: Exploring a replicable prompting protocol for LLM-assisted corpus analysis
TACOMORE: 探索一种可复现的提示协议用于LLM辅助语料库分析
机构 * Department of Linguistics and Communication, University of Birmingham(伯明翰大学语言学与传播系) ; Department of Information Engineering and Computer Science, University of Trento(特伦托大学信息工程与计算机科学系) ; Institute of Foreign Languages and Cultures, University of Tartu(塔尔图大学外国语言与文化研究所)
专题命中 预训练与数据 :LLM(title,title_cn);prompting(title,abstract);large language model(abstract);language model(abstract)
AI总结 提出TACOMORE框架,通过结构化提示将LLM从通用概率预测转向基于语料共现模式的推理,提升关键词、搭配和索引行分析的准确性与可复现性,但幻觉问题仍需人工验证。