The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generation
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2607.17420 (cs)
[Submitted on 19 Jul 2026]
Title:The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generation
Authors:Shayell Aharon Salomon (Bluebear Security), Noam Israel (Bluebear Security), Ido Safruti (Bluebear Security), Amir Shaked (Bluebear Security)
View a PDF of the paper titled The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generation, by Shayell Aharon Salomon (Bluebear Security) and 3 other authors
View PDF
HTML (experimental)
Abstract: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.
| Comments: | 17 pages, 3 tables, no figures. Ancillary files include raw completions, derived scores, analysis scripts, persona texts, and preregistration |
| Subjects: | Computation and Language (cs.CL); Software Engineering (cs.SE) |
| Cite as: | arXiv:2607.17420 [cs.CL] |
| (or arXiv:2607.17420v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.17420
arXiv-issued DOI via DataCite (pending registration)
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled The Librarian Who Refused to Code: Model-Dependent Identity Enactment in LLM Code Generation, by Shayell Aharon Salomon (Bluebear Security) and 3 other authors
Ancillary-file links:
Ancillary files (details):
- SHA256SUMS.txt
- analysis/analyze_main.py
- analysis/c2_by_cell.csv
- analysis/identity_enactment.py
- analysis/mixed_effects.json
- analysis/mixed_effects_corrected.json
- analysis/recompute_corrected.py
- analysis/requirements.txt
- analysis/results.csv
- analysis/score_responses.py
- analysis/scored_responses.csv
- personas/P0_baseline.txt
- personas/P_A_maya.txt
- personas/P_B_ron.txt
- personas/P_C_linnea.txt
- preregistration/05_preregistration.md
- runs/main/main_claude-opus-4-8_20260622T145939232171Z.jsonl
- runs/main/main_gpt-5_5_20260622T145642342609Z.jsonl
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.