Controllable text generation: toward non-toxic, unbiased and factual language models for sensitive applications

可控文本生成：针对敏感应用的无毒、公正和事实的语言模型

• 批准号: 2902174
• 金额: --
• 依托单位: Imperial College London
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2902174
• 关键词: Controllable; text; generation; toward; non

we will investigate the following methodologies as a starting point:1. Parameter-e_cient paradigms - which allow fine-tuning a pretrained model for adownstream task without modifying all of its parameters - are not only more computationally efficient: they have also been found to outperform full model tuning in many cases [12, 13, 14]. These paradigms include prompt tuning [12], adapters [13] and prefix tuning [14]. It is worth noting that recent papers have investigated all three approaches in relation to the detoxification and debiasing of language models, with encouraging results [15, 16]. We aim to investigate these paradigms and build upon the existing research.2. Retrieval-augmented generation has been shown to achieve state-of-the-art-performancein a number of benchmarks [17]. This approach augments the knowledge implicitly stored in a model's parameters with a knowledge retriever that attends to an external corpus, such as Wikipedia or a knowledge graph [18, 19]. Since these corpora can encode facts with historical and scientific accuracy as well as societal norms and values [20, 21, 22], it is worth investigating whether retrieval-augmented approaches can result in less biased and less toxic models.

我们将研究以下方法作为起点：1.参数已知范例--允许微调下行任务的预训练模型而不修改其所有参数--不仅在计算上更高效：它们在许多情况下也被发现优于完全模型调整[12，13，14]。这些范例包括即时调整[12]、适配器[13]和前缀调整[14]。值得注意的是，最近的论文调查了所有三种与语言模式解毒和去偏见有关的方法，结果令人鼓舞[15，16]。我们的目标是研究这些范式，并在现有研究的基础上再接再厉。在许多基准测试中，检索增强生成已被证明达到了最先进的性能[17]。这种方法使用一个知识检索器来增加模型参数中隐含存储的知识，该知识检索器负责外部语料库，如维基百科或知识图谱[18，19]。由于这些语料库可以用历史和科学的准确性以及社会规范和价值观来编码事实[20，21，22]，因此值得研究检索增强的方法是否可以导致较少的偏见和较少的毒性模型。