Abstract
Individuals engaging in online communication frequently express personal opinions with informal styles (e.g., memes and emojis). While Language Models (LMs) with informal communications have been widely discussed, a unique and emphatic style, the Repetitive Lengthening Form (RLF), has been overlooked for years. In this paper, we explore answers to two research questions: 1) Is RLF important for sentiment analysis (SA)? 2) Can LMs understand RLF? Inspired by previous linguistic research, we curate \textbf{Lengthening}, the first multi-domain dataset with 850k samples focused on RLF for SA. Moreover, we introduce \textbf{Exp}lainable \textbf{Instruct}ion Tuning (\textbf{ExpInstruct}), a two-stage instruction tuning framework aimed to improve both performance and explainability of LLMs for RLF. We further propose a novel unified approach to quantify LMs' understanding of informal expressions. We show that RLF sentences are expressive expressions and can serve as signatures of document-level sentiment. Additionally, RLF has potential value for online content analysis. Our results show that fine-tuned Pre-trained Language Models (PLMs) can surpass zero-shot GPT-4 in performance but not in explanation for RLF. Finally, we show ExpInstruct can improve the open-sourced LLMs to match zero-shot GPT-4 in performance and explainability for RLF with limited samples. Code and sample data are available at this https URL
Abstract (translated)
在进行在线交流时,个体常以非正式风格(如表情包和表情符号)表达个人观点。尽管针对非正式交流场景的语言模型(LMs)已得到广泛讨论,但一种独特且强调性的表达形式——重复延长形式(RLF)——多年来却一直被忽视。本文围绕两个研究问题展开探究:1)RLF对情感分析(SA)是否重要?2)LMs能否理解RLF?受先前语言学研究的启发,我们构建了首个聚焦RLF的多领域数据集\textbf{Lengthening},该数据集包含85万条样本,专用于SA任务。此外,我们提出了\textbf{可解释指令微调}(\textbf{ExpInstruct})——一种两阶段指令微调框架,旨在提升大语言模型(LLMs)在RLF任务上的性能与可解释性。我们还提出了一种新颖的统一方法,用于量化LMs对非正式表达的理解程度。研究表明,RLF句子具有丰富的表现力,可作为文档级情感的显著特征,且RLF对在线内容分析具有潜在价值。实验结果显示,经过微调的预训练语言模型(PLMs)在性能上可超越零样本GPT-4,但在RLF解释性方面仍存在差距。最后,我们证明ExpInstruct能够以有限样本提升开源LLMs在RLF任务上的性能与可解释性,使其达到零样本GPT-4的水平。代码与样本数据可通过此链接获取。
URL
https://arxiv.org/abs/2604.01268