大型语言模型在目标情感分析中的应用
Large Language Models in Targeted Sentiment Analysis
AI总结：
本文研究大型语言模型在俄语新闻目标情感分析中的应用，通过零样本评估和基于思维链的Flan-T5微调，在RuSentNE-2023上取得最优结果并超越先前最先进模型。
摘要：
本文研究了使用基于解码器的生成式Transformer来提取俄语新闻文章中命名实体的情感倾向。我们研究了经过指令微调的大型语言模型（LLMs）的情感分析能力。在我们的研究中，我们考虑了RuSentNE-2023数据集。第一组实验旨在评估具有封闭和开放透明度的LLMs的零样本能力。第二组实验涵盖了使用“思维链”（CoT）三步推理框架（THoR）对Flan-T5进行微调。我们发现，零样本方法的结果与基线微调编码器Transformer（BERT-base）的结果相似。使用THoR微调的Flan-T5模型的推理能力，在基础大小模型上相比零样本实验结果至少提升了5%。在RuSentNE-2023上，情感分析的最佳结果由微调的Flan-T5-xl取得，其超越了之前最先进的基于Transformer的分类器。我们的CoT应用框架已公开提供：https://github.com/nicolay-r/Reasoning-for-Sentiment-Analysis-Framework
英文摘要：
In this paper we investigate the use of decoder-based generative transformers for extracting sentiment towards the named entities in Russian news articles. We study sentiment analysis capabilities of instruction-tuned large language models (LLMs). We consider the dataset of RuSentNE-2023 in our study. The first group of experiments was aimed at the evaluation of zero-shot capabilities of LLMs with closed and open transparencies. The second covers the fine-tuning of Flan-T5 using the "chain-of-thought" (CoT) three-hop reasoning framework (THoR). We found that the results of the zero-shot approaches are similar to the results achieved by baseline fine-tuned encoder-based transformers (BERT-base). Reasoning capabilities of the fine-tuned Flan-T5 models with THoR achieve at least 5% increment with the base-size model compared to the results of the zero-shot experiment. The best results of sentiment analysis on RuSentNE-2023 were achieved by fine-tuned Flan-T5-xl, which surpassed the results of previous state-of-the-art transformer-based classifiers. Our CoT application framework is publicly available: https://github.com/nicolay-r/Reasoning-for-Sentiment-Analysis-Framework
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
