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.
翻译:语言模型(LMS)在文件收集方面受过培训,由人类代理人个人编写,以实现外部世界的具体目标。在培训期间,LMS只能获取这些文件的文本,而没有直接证据表明产生这些文件的代理人的内部状态 -- -- 通常用来证明LMS无法模拟人类语言制作和理解的目标方向方面。LMS能否在文本方面受过培训,完全了解语言与使用之间的关系?我争辩说,LMS是特定、狭义意义上的有意交流模式。在根据文字背景进行下一个单词预测时,LM可以推断并代表可能产生这种背景的代理人的特性。这些表达方式反过来可以影响LM一代的后代,就像代理人的交流意图影响其语言的方式一样。我从最近的文献中了解到 -- -- 即使在今天的不严酷和易出错的模式中 -- -- LMMS推论并使用精密的交流意图和更加抽象的信念和目标的表述。尽管其培训数据性质有限,它们也可以作为通信和故意行动的系统的基石。