从偏见到处境性：大语言模型的一种批判性语法
From Bias to Positionality: A critical grammar for Large Language Models
AI 导读
arXiv 论文提出用“处境性”取代“偏见”来理解大语言模型：偏见是相对某个外部标准的偏差，而通用语言模型缺乏可审计的决策和反事实输出，使这一简写失效。作者将模型视为“仿佛在说话”的主体，认为其处境性分层沉积于语料、微调、system prompt、应用与实时对话之中，并区分创作者处境、预期行为与实际行为三组因素，以讨论模型的构建、解读与问责。
正文 · 原文
Abstract:Bias has become a default lens for understanding what machine learning systems do and how we should relate to them. Bias is at root a deviation from a standard; in decision making systems we can supply a standard from outside: a law, a protected attribute, a benchmark, a statistical property. However, even there, biased is often used as a shorthand, without stating what the position taken is - a silent ``relative to''. In a general use of language models, nothing supplies the standard: there is no decision to audit and no counterfactual output, so the shorthand fails. We argue that positionality -- the located, articulated, owned and contestable position from which anything is said -- is the better grammar for the question these models now force: who is speaking, from where? Against the vendors' answer of nowhere and the seductive possibility of everywhere, we argue that when a model is taken as-if speaking, it speaks from somewhere, and this means positionality can describe models, and the way they are believed beyond their warrant, even though they are not accountable speakers. A model's positionality is laminar -- laid down across corpus, tuning, system prompt, application and the live conversation. We separate three sets of factors: the positionality of a model's creators, the behaviour they intend for it, and the behaviour it enacts, and situate current work within this matrix. This lets us highlight what each stratum inherits from the one below, with ruptures and collapses where that inheritance is disavowed. We then return to where models speak from, and discuss the implications for how models are made, read and held accountable.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.14079 [cs.CL] |
| (or arXiv:2611.14079v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14079 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dave Murray-Rust [view email]
[v1]
Tue, 10 Nov 2026 13:41:18 UTC (212 KB)
来源：arXiv cs.AI · arxiv.org