arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08239cs.CLcs.AI
收藏

LaMDA:对话应用的语言模型

LaMDA: Language Models for Dialog Applications

Google(谷歌公司)
Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, YaGuang Li, Hong… 展开作者

Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, YaGuang Li, Hongrae Lee, Huaixiu Steven Zheng, Amin Ghafouri, Marcelo Menegali, Yanping Huang, Maxim Krikun, Dmitry Lepikhin, James Qin, Dehao Chen, Yuanzhong Xu, Zhifeng Chen, Adam Roberts, Maarten Bosma, Vincent Zhao, Yanqi Zhou, Chung-Ching Chang, Igor Krivokon, Will Rusch, Marc Pickett, Pranesh Srinivasan, Laichee Man, Kathleen Meier-Hellstern, Meredith Ringel Morris, Tulsee Doshi, Renelito Delos Santos, Toju Duke, Johnny Soraker, Ben Zevenbergen, Vinodkumar Prabhakaran, Mark Diaz, Ben Hutchinson, Kristen Olson, Alejandra Molina, Erin Hoffman-John, Josh Lee, Lora Aroyo, Ravi Rajakumar, Alena Butryna, Matthew Lamm, Viktoriya Kuzmina, Joe Fenton, Aaron Cohen, Rachel Bernstein, Ray Kurzweil, Blaise Aguera-Arcas, Claire Cui, Marian Croak, Ed Chi, Quoc Le

摘要:

我们提出了LaMDA:对话应用程序的语言模型。LaMDA是一个专门用于对话的基于transformer的神经语言模型家族,具有多达137 B的参数,并在1.56 T的公共对话数据和Web文本上进行预训练。虽然模型缩放可以单独提高质量,但它在安全性和事实基础方面的改进较少。我们证明,使用注释数据进行微调,并使模型能够咨询外部知识来源,可以显著改善安全性和事实基础这两个关键挑战。第一个挑战是安全性,它涉及到确保模型的响应符合一系列人类价值观,例如防止有害的建议和不公平的偏见。我们使用基于一组说明性的人类价值的度量来量化安全性,我们发现使用LaMDA分类器过滤候选响应,并使用少量的crowdworker-annotated数据进行微调,提供了一种很有前途的方法来提高模型的安全性。第二个挑战,事实基础,涉及到使模型能够咨询外部知识源,如信息检索系统,语言翻译器和计算器。我们量化的真实性,使用一个approximedness度量,我们发现,我们的方法使该模型能够生成基于已知来源的响应,而不是响应,只是听起来似是而非。最后,我们探讨了LaMDA在教育和内容推荐领域的使用,并分析了它们的帮助性和角色一致性。

英文摘要:

We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog data and web text. While model scaling alone can improve quality, it shows less improvements on safety and factual grounding. We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding. The first challenge, safety, involves ensuring that the model's responses are consistent with a set of human values, such as preventing harmful suggestions and unfair bias. We quantify safety using a metric based on an illustrative set of human values, and we find that filtering candidate responses using a LaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promising approach to improving model safety. The second challenge, factual grounding, involves enabling the model to consult external knowledge sources, such as an information retrieval system, a language translator, and a calculator. We quantify factuality using a groundedness metric, and we find that our approach enables the model to generate responses grounded in known sources, rather than responses that merely sound plausible. Finally, we explore the use of LaMDA in the domains of education and content recommendations, and analyze their helpfulness and role consistency.

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。

↑