按年被提到
20232024 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:2310.18025 · cs.CL

Large language models for aspect-based sentiment analysis

Paul F. Simmering, Paavo Huoviala · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-04-11 · 最近 2024-08-14
2不同的人
2活跃月份
2讨论串
55被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) offer unprecedented text completion capabilities. As general models, they can fulfill a wide range of roles, including those of more specialized models. We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings on the aspect-based sentiment analysis (ABSA) task. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task of the SemEval-2014 Task 4, improving upon InstructABSA [@scaria_instructabsa_2023] by 5.7%. However, this comes at the price of 1000 times more model parameters and thus increased inference cost. We discuss the the cost-performance trade-offs of different models, and analyze the typical errors that they make. Our results also indicate that detailed prompts improve performance in zero-shot and few-shot settings but are not necessary for fine-tuned models. This evidence is relevant for practioners that are faced with the choice of prompt engineering versus fine-tuning when using LLMs for ABSA.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论hitradostava · 2024-08

“I have to agree with the parent. LLMs are excellent at a large range of NLP tasks. Of course they are not going to replace all ML models, but when it comes to NLP they are clearly better than lots of trained models (e.g. https://arxiv.org/pdf/2310.18025).”

LLM-based sentiment analysis of Hacker News posts between Jan 2020 and June 2023原评论 ↗
被提交为 story · 1 次