arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.11097cs.CLcs.AI
收藏

InstructCMP:通过基于指令的大语言模型实现句子压缩中的长度控制

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models

Chungnam National University(忠南大学);Nara Institute of Science and Technology (NAIST)(奈良科学技术研究所);Tokyo Institute of Technology(东京工业大学)

Juseon-Do, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura

AI总结:

针对传统句子压缩模型难满足长度约束的问题,提出基于指令的InstructCMP方法,结合长度启动策略与指令格式数据集微调,在零样本和微调场景下均显著提升长度控制性能且无需修改模型。

摘要:

抽取式摘要能够生成忠实的摘要,但通常需要满足期望摘要长度等额外约束。传统句子压缩模型受限于自身能力,通常不会考虑这类约束,若要应对约束则需要对模型进行修改。为填补这一空白,我们提出基于指令的压缩方法InstructCMP,这是一种句子压缩任务方法,可借助大语言模型(LLMs)的零样本任务解决能力,通过指令实现长度约束的考量。为此,我们将传统句子压缩数据集转换为指令格式,构建了新的评估数据集。利用这些数据集,我们首先发现当前的LLM在精准控制压缩文本长度方面仍面临挑战。为解决这一问题,我们提出名为“长度启动(length priming)”的方法,无需外部资源即可将额外长度信息融入指令中。尽管长度启动在零样本设置下已能有效发挥作用,但带有指令的训练数据集会进一步提升长度控制能力。因此,我们额外构建了指令格式的训练数据集,用于对模型进行微调。实验结果与分析表明,应用长度启动可在无需任何模型修改的情况下,显著提升InstructCMP在零样本和微调设置下的性能。

英文摘要:

Extractive summarization can produce faithful summaries but often requires additional constraints such as a desired summary length. Traditional sentence compression models do not typically consider the constraints because of their restricted model abilities, which require model modifications for coping with them. To bridge this gap, we propose Instruction-based Compression (InstructCMP), an approach to the sentence compression task that can consider the length constraint through instructions by leveraging the zero-shot task-solving abilities of Large Language Models (LLMs). For this purpose, we created new evaluation datasets by transforming traditional sentence compression datasets into an instruction format. By using the datasets, we first reveal that the current LLMs still face challenges in accurately controlling the length for a compressed text. To address this issue, we propose an approach named "length priming," that incorporates additional length information into the instructions without external resources. While the length priming effectively works in a zero-shot setting, a training dataset with the instructions would further improve the ability of length control. Thus, we additionally created a training dataset in an instruction format to fine-tune the model on it. Experimental results and analysis show that applying the length priming significantly improves performances of InstructCMP in both zero-shot and fine-tuning settings without the need of any model modifications.

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。

↑