# Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models

arXiv: https://arxiv.org/abs/2609.34065 · HTML: https://mlsanity.com/paper/2609.34065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- ["You are grounded!": Latent Name Artifacts in Pre-trained Language Models](https://mlsanity.com/paper/2004.03012/) (2020)
- [Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models](https://mlsanity.com/paper/2110.00672/) (2021)
- ["You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations](https://mlsanity.com/paper/2406.12232/) (2024)
- [Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?](https://mlsanity.com/paper/2406.10486/) (2024)
- [Presumed Cultural Identity: How Names Shape LLM Responses](https://mlsanity.com/paper/2502.11995/) (2025)
- [First-Person Fairness in Chatbots](https://mlsanity.com/paper/2410.19803/) (2024)
- [Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks](https://mlsanity.com/paper/2406.12066/) (2024)
- [Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts](https://mlsanity.com/paper/2410.11084/) (2024)
- [Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases](https://mlsanity.com/paper/2305.16577/) (2023)
- [Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning](https://mlsanity.com/paper/2306.01117/) (2023)
- [A Study of Implicit Ranking Unfairness in Large Language Models](https://mlsanity.com/paper/2311.07054/) (2023)
- [Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring](https://mlsanity.com/paper/2604.19984/) (2026)

## Abstract (arXiv)

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.