arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.10583cs.CLcs.LG
收藏

所有这些随机鹦鹉都在模仿谁?它们应该告诉我们!

Who Are All The Stochastic Parrots Imitating? They Should Tell Us!

University of Colorado Boulder(科罗拉多大学博尔德分校);University of Colorado Denver(科罗拉多大学丹佛分校);Johannes Gutenberg University Mainz(美因茨约翰内斯·古滕贝格大学)

Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense

AI总结:

针对语言模型易生成不实陈述、低资源语言场景下问题更严重的问题,本文提出构建可引用训练数据来源的语言模型策略,分析其优势并梳理待解任务,呼吁讨论模型构建与训练数据作用的作用。

摘要:

独立语言模型(LM)以及下游任务系统中的语言模型均被证实会生成与事实不符的陈述。这一问题在低资源语言中尤为严重,此类语言的训练数据稀缺,且质量不及高资源语言的训练数据。在这篇观点类文章中,我们认为当前状态下的语言模型在关键场景中永远无法完全可信,并提出了一种应对该问题的潜在新策略:构建能够标注来源的语言模型——即向用户指出支撑其输出结果的训练数据部分。我们首先探讨了当前哪些自然语言处理(NLP)任务能从此类模型中受益、哪些不能。随后我们强调了这类模型将带来的预期优势,例如陈述的可快速验证性。最后我们概述了开发具备引用来源能力的语言模型过程中需要解决的各项具体任务。我们希望引发关于该领域围绕当前语言模型构建方法(尤其是针对低资源语言的构建方法),以及训练数据在解释模型生成内容方面作用的讨论。

英文摘要:

Both standalone language models (LMs) as well as LMs within downstream-task systems have been shown to generate statements which are factually untrue. This problem is especially severe for low-resource languages, where training data is scarce and of worse quality than for high-resource languages. In this opinion piece, we argue that LMs in their current state will never be fully trustworthy in critical settings and suggest a possible novel strategy to handle this issue: by building LMs such that can cite their sources - i.e., point a user to the parts of their training data that back up their outputs. We first discuss which current NLP tasks would or would not benefit from such models. We then highlight the expected benefits such models would bring, e.g., quick verifiability of statements. We end by outlining the individual tasks that would need to be solved on the way to developing LMs with the ability to cite. We hope to start a discussion about the field's current approach to building LMs, especially for low-resource languages, and the role of the training data in explaining model generations.

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。

↑