arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11218cs.CL
收藏

基于动态属性图的大语言模型受控文本生成

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs

Renmin University of China(中国人民大学);Nankai University(南开大学);Institute for Advanced Algorithms Research (Shanghai)((上海)高级算法研究院)

Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang

AI总结:

提出DATG框架,利用动态属性图调节关键属性词实现LLM受控文本生成,在毒性缓解和情感转换任务中控制准确率最高提升19.29%,并降低困惑度。

摘要:

受控文本生成(CTG)旨在生成具有特定期望属性的文本。在本研究中,我们提出了一种可插拔的大语言模型(LLM)受控文本生成框架,名为基于动态属性图的受控文本生成(DATG)。该框架利用一个属性评分器来评估由LLM生成的句子的属性,并构建动态属性图。DATG调节关键属性词和关键反属性词的出现,从而在不损害模型原有能力的情况下实现有效的属性控制。我们在两个任务(毒性缓解和情感转换)的四个数据集上进行了实验,采用五个LLM作为基础模型。我们的研究结果显示,控制准确性显著提升,在四个数据集的最有利任务中,相比基线方法实现了19.29%的峰值提升。此外,我们观察到困惑度显著下降,文本流畅性明显改善。

英文摘要:

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG). This framework utilizes an attribute scorer to evaluate the attributes of sentences generated by LLMs and constructs dynamic attribute graphs. DATG modulates the occurrence of key attribute words and key anti-attribute words, achieving effective attribute control without compromising the original capabilities of the model. We conduct experiments across four datasets in two tasks: toxicity mitigation and sentiment transformation, employing five LLMs as foundational models. Our findings highlight a remarkable enhancement in control accuracy, achieving a peak improvement of 19.29% over baseline methods in the most favorable task across four datasets. Additionally, we observe a significant decrease in perplexity, markedly improving text fluency.

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。

↑