# The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generation

arXiv: https://arxiv.org/abs/2607.17420 · HTML: https://mlsanity.com/paper/2607.17420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation](https://mlsanity.com/paper/2404.10100/) (2024)
- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance](https://mlsanity.com/paper/2508.19764/) (2025)
- [Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM](https://mlsanity.com/paper/2603.18507/) (2026)
- [SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent](https://mlsanity.com/paper/2502.08599/) (2025)
- [Persona Prompting as a Lens on LLM Social Reasoning](https://mlsanity.com/paper/2601.20757/) (2026)
- [Understanding Specification-Driven Code Generation with LLMs: An Empirical Study Design](https://mlsanity.com/paper/2601.03878/) (2026)

## Abstract (arXiv)

Biographical personas are widely used in system prompts, but their effects on code generation are rarely evaluated under controlled, pre-registered conditions. We tested four prompt conditions (no persona, two engineer personas, and a research-librarian persona), 12 code-generation tasks, two frontier models, and five runs per cell (480 completions). Persona effects differed between the two tested models. Under the pre-registered mixed-effects analysis, the condition-by-model interaction was significant for provider-reported output tokens; a post-hoc visible-character measure showed the same qualitative pattern. Six GPT-5.5 completions were length-capped and are reported separately. On Claude Opus, the minimalist engineer persona reduced visible output by 30% (33% in provider tokens) without improving correctness, while the thorough engineer persona increased output without a correctness gain. In an exploratory post-hoc analysis, the librarian persona elicited in-character disclaimers in 55 of 60 Opus responses and 12 genuine no-code responses, lowering mean correctness from 0.92 to 0.67. GPT-5.5 produced neither behavior in its 59 non-truncated responses. These results are consistent with personas acting as Model-Dependent behavioral-policy biases rather than universal quality interventions. We release raw completions, derived scores, analysis artifacts, a pre-registration document, and an execution gate log; end-to-end test-based rescoring requires an unreleased task harness.