FOCUS:通过在语言模型自我抄袭中的对比使用来锻造原创性
FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models
AI总结:
提出一种“自我抄袭”对比解码策略FOCUS,通过修改提示构建业余和专业模型,惩罚非原创token组合,显著减少PLMs生成文本中的非原创序列。
摘要:
预训练语言模型(PLMs)在各种自然语言生成(NLG)任务中表现出色,例如驱动聊天机器人和生成故事。然而,由于它们可能从训练数据中逐字复制段落,引发了伦理担忧。这很成问题,因为PLMs是在由人类作者构建的语料库上训练的。因此,迫切需要研究以促进这些模型生成原创内容。在本研究中,我们引入了一种独特的“自我抄袭”对比解码策略,旨在提升PLMs生成文本的原创性。我们的方法包括修改LLMs中的提示,以开发一个业余模型和一个专业模型。具体而言,业余模型被促使使用我们设计的三个抄袭模板进行抄袭,而专业模型保持其标准语言模型状态。该策略利用提示来激发模型识别非原创候选token组合的能力,随后施加惩罚。此策略的应用集成在模型最后一层之前,确保与大多数现有PLMs(T5、GPT、LLaMA)平滑集成,而无需进一步调整。实施我们的策略后,我们观察到在学术AASC数据集和基于故事的ROCStories数据集中,由超过三个词组成的非原创序列显著减少。
英文摘要:
Pre-trained Language Models (PLMs) have shown impressive results in various Natural Language Generation (NLG) tasks, such as powering chatbots and generating stories. However, an ethical concern arises due to their potential to produce verbatim copies of paragraphs from their training data. This is problematic as PLMs are trained on corpora constructed by human authors. As such, there is a pressing need for research to promote the generation of original content by these models. In this study, we introduce a unique "self-plagiarism" contrastive decoding strategy, aimed at boosting the originality of text produced by PLMs. Our method entails modifying prompts in LLMs to develop an amateur model and a professional model. Specifically, the amateur model is urged to plagiarize using three plagiarism templates we have designed, while the professional model maintains its standard language model status. This strategy employs prompts to stimulate the model's capacity to identify non-original candidate token combinations and subsequently impose penalties. The application of this strategy is integrated prior to the model's final layer, ensuring smooth integration with most existing PLMs (T5, GPT, LLaMA) without necessitating further adjustments. Implementing our strategy, we observe a significant decline in non-original sequences comprised of more than three words in the academic AASC dataset and the story-based ROCStories dataset.
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。