Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people, so it is shown that this assumption often fails at the lexical interface: matched names are not necessarily matched inputs.
Abstract
Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such evaluations typically assume that matched names are comparable model inputs. We show that this assumption often fails at the lexical interface: matched names are not necessarily matched inputs. Some names receive direct single-token access, while others are assembled from multiple subwords, creating unequal name-surface support. Across nearly half a million first names and 12 LLM-associated tokenizers, direct lexical access is highly selective, model dependent, and uneven across race- and gender-associated name metadata. We introduce NameTrace, a model-native, fine-grained, pre-behavioral framework for measuring whether unequal name-surface support remains a vocabulary property or becomes visible in task-relevant internal representations. NameTrace measures concept accessibility from the model's own probabilities over task-specific adjective axes with continuous task-aligned weights. On matched atomic and short-fragmented names within the same race/ethnicity--gender-associated strata, support predicts systematic differences in concept accessibility across fellowship, hiring, clinical assessment, and lending. These differences persist across all eight matched strata, extend across model families, and transfer to unseen names. Hidden-state interventions further show that the measured task directions have downstream leverage, shifting later constrained choices. Unequal lexical support is therefore demographically structured at the input and remains visible in task-relevant model computation. NameTrace makes lexical comparability measurable, supporting a broader principle: behavioral comparability begins with lexical comparability.
Face/Off is introduced, a semantics-preserving identifier-renaming framework, and progressive naming conditions across multiple models and code-comprehension tasks are evaluated, revealing a systematic vulnerability in how current LLMs balance lexical cues against program structure.
Xin-Peng Shen, San-Zhuo Xi, Ya-Li Du et al.· arXiv.org· 0 citations
Asset names influence market behavior, yet standardized name measurement remains lacking. Existing processing fluency measures focus mainly on alphabetic languages and are unsuitable for Chinese names. Cultural meanings usually require manual coding, limiting large-scale analysis, while name competition through reuse a...
Ding-Ding Cao, Yu-Jin Zhong, Han-Yang Wang et al.· 1 citation
Systematicity, the probabilistic mapping of form to meaning, permeates language at all levels, and sublexical cues have been shown to govern human pseudoword processing. Yet whether LLMs exhibit comparable sensitivity to these cues remains unclear. We tested five LLMs on two Italian two-alternative forced-choice pseudo...
Jing Chen, Giulia Loca, Simona Amenta et al.· 0 citations
Black-box model identification works by scoring a model's response to natural-language prompts. One line of work feeds models a degenerate input -- their own token, repeated -- to find a failure mode rather than an identity. We take that input and ask where the model goes when it does not. For each token t, read argmax...
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses ac...
Large language models learn word meanings through distributional semantics (i.e., patterns in text), and distribution does not always capture information about taxonomy and function, which are essential to human representations of word meaning. However, sound and spelling often conveys such information, and language...
David A. Haslett, Antoni B. Chan, J. Hsiao· Transactions of the Associat...· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.