论语言模型的指称能力:对 Mandelkern & Linzen 的内在主义回应
On the referential capacity of language models: An internalist rejoinder to Mandelkern & Linzen
AI总结:
本文从内在主义视角回应 Mandelkern & Linzen 关于语言模型词语指称能力的外在主义分析,指出其主张仅适用于有限的自然语言表达式,并警告其表述可能导致对 LM 指称能力的过度概括。
摘要:
在近期的一篇论文中,Mandelkern & Linzen (2024)——以下简称 M&L——探讨了语言模型(LMs)的词语是否具有指称能力的问题。他们的论点借鉴了哲学语义学中的外在主义传统,该传统将指称视为词语“建立‘词与世界’连接”的能力。在外在主义框架下,因果上未中断的使用链条,将名字的每一次出现追溯回其承担者,从而保证例如“Peano”指代 Peano 这个人(Kripke 1980)。这种解释是外在主义的,既因为词语在世界上“那里”挑选出指称对象,也因为决定指称的是社区成员协调的语言行为,而非个体的心理状态。对于 M&L 而言,“要问的核心问题”是 LMs 是否也属于人类语言社区,使得 LMs 生成的词语同样能在因果上追溯回其承担者。他们的回答是谨慎的“是”:LMs 的输入是“具有特定指称使用历史的语言形式”;“这些历史为这些形式的指称对象提供基础”;“Peano”在 LM 输出中的任何出现,与人类言语或文本中同一专有名词的任何其他出现一样,在因果上与 Peano 这个人相连;因此,“Peano”在 LM 输出中的出现指代 Peano。在这篇评论中,我们首先限定 M&L 的主张仅适用于一小类自然语言表达式。经过如此限定,他们的主张是有效的,我们在第 2 节强调了对此的额外动机。接下来,我们讨论他们主张的实际范围,并指出其表述方式可能导致对 LMs 中指称的未经授权的概括。我们的批评同样适用于 LMs 的其他外在主义解释(例如,Lederman & Mahowald 2024;Mollo & Milliere 2023)。最后,我们以对 LMs 作为人类语言社区成员地位的评论作为结语。
英文摘要:
In a recent paper, Mandelkern & Linzen (2024) - henceforth M&L - address the question of whether language models' (LMs) words refer. Their argument draws from the externalist tradition in philosophical semantics, which views reference as the capacity of words to "achieve 'word-to-world' connections". In the externalist framework, causally uninterrupted chains of usage, tracing every occurrence of a name back to its bearer, guarantee that, for example, 'Peano' refers to the individual Peano (Kripke 1980). This account is externalist both because words pick out referents 'out there' in the world, and because what determines reference are coordinated linguistic actions by members of a community, and not individual mental states. The "central question to ask", for M&L, is whether LMs too belong to human linguistic communities, such that words by LMs may also trace back causally to their bearers. Their answer is a cautious "yes": inputs to LMs are linguistic "forms with particular histories of referential use"; "those histories ground the referents of those forms"; any occurrence of 'Peano' in LM outputs is as causally connected to the individual Peano as any other occurrence of the same proper name in human speech or text; therefore, occurrences of 'Peano' in LM outputs refer to Peano. In this commentary, we first qualify M&L's claim as applying to a narrow class of natural language expressions. Thus qualified, their claim is valid, and we emphasise an additional motivation for that in Section 2. Next, we discuss the actual scope of their claim, and we suggest that the way they formulate it may lead to unwarranted generalisations about reference in LMs. Our critique is likewise applicable to other externalist accounts of LMs (e.g., Lederman & Mahowald 2024; Mollo & Milliere 2023). Lastly, we conclude with a comment on the status of LMs as members of human linguistic communities.
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。