Do Language Models' Words Refer?
What do language models (LMs) do with language? Everyone agrees that they can produce sequences of (mostly) coherent strings of English. But do those sentences mean something, or are LMs simply babbling in a convincing simulacrum of language use? Here we will address one aspect of this broad question: whether LMs' words can refer, that is, achieve "word-to-world" connections. There is prima facie reason to think they do not since LMs do not interact with the world in the way that ordinary language users do. Drawing on insights from the externalist tradition in philosophy of language, we argue that those appearances are misleading: even if the inputs to an LM are simply strings of text, they are strings of text with natural histories, and that may suffice to put LMs' words into referential contact with the external world.
Code (0)
등록된 구현이 없습니다.
Tasks
PhilosophySimilar Papers 제목 키워드 기반
Resolving References to Objects in Photographs using the Words-As-Classifiers Model
A common use of language is to refer to visually present objects. Modelling it in computers requires modelling the link between language and perception. The "words as classifiers" model of grounded semantics views words …
Why do objects have many names? A study on word informativeness in language use and lexical systems
Human lexicons contain many different words that speakers can use to refer to the same object, e.g., "purple" or "magenta" for the same shade of color. On the one hand, studies on language use have explored how speakers …
InformativenessTalking about the world with a distributed model
We use language to talk about the world, and so reference is a crucial property of language. However, modeling reference is particularly difficult, as it involves both continuous and discrete as-pects of language. For in…
modelText GenerationBootstrapping Referring Multi-Object Tracking
Referring multi-object tracking (RMOT) aims at detecting and tracking multiple objects following human instruction represented by a natural language expression. Existing RMOT benchmarks are usually formulated through man…
DiversityMulti-Object TrackingObjectObject Tracking+1World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models
The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new …
Grounded Open Vocabulary AcquisitionLanguage ModelingLanguage Modelling