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 2212.01681cs.CLcs.MA
收藏

作为Agent模型的语言模型

Language Models as Agent Models

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

Jacob Andreas

摘要:

语言模型(LM)是在文档集合上训练的,这些文档集合是由个体人类代理编写的,以在外部世界中实现特定目标。在训练过程中,LMs只能访问这些文档的文本,没有产生它们的代理的内部状态的直接证据-这一事实经常被用来争论LMs无法对人类语言产生和理解的目标导向方面进行建模。接受过文本训练的语言学习者能学到语言和使用之间的关系吗?我认为,LMs是一个具体的,狭义的有意沟通的模式。当给定文本上下文执行下一个单词预测时,LM可以推断并表示可能产生该上下文的代理的属性。这些表征反过来又会影响随后的LM生成,就像代理人的交际意图影响他们的语言一样。我调查的结果,从最近的文献显示,即使在今天的非强大的和容易出错的模型-LM推断和使用细粒度的沟通意图和更抽象的信念和目标的表示。尽管它们的训练数据有限,但它们可以作为系统的构建模块,有意识地进行通信和行动。

英文摘要:

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of the internal states of the agents that produced them -- a fact often used to argue that LMs are incapable of modeling goal-directed aspects of human language production and comprehension. Can LMs trained on text learn anything at all about the relationship between language and use? I argue that LMs are models of intentional communication in a specific, narrow sense. When performing next word prediction given a textual context, an LM can infer and represent properties of an agent likely to have produced that context. These representations can in turn influence subsequent LM generation in the same way that agents' communicative intentions influence their language. I survey findings from the recent literature showing that -- even in today's non-robust and error-prone models -- LMs infer and use representations of fine-grained communicative intentions and more abstract beliefs and goals. Despite the limited nature of their training data, they can thus serve as building blocks for systems that communicate and act intentionally.

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。

↑