SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.14930 · NeurIPS · 2023

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Zeynep Akata, Eric Schulz, Stephan Alaniz, Leonard Salewski, Isabel Rio-Torto

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.14930.json · badge: /api/ran/2305.14930.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ExplainableML/in-context-impersonation canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_pylogger Ran
ran; our contract draft was wrong, not the code
ExplainableML/in-context-impersonation/src/utils/pylogger.py
code served (permissive licence) · get_code("b0cd1557c2946d8d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Logger. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import logging
from lightning.pytorch.utilities import rank_zero_only

# The function get_pylogger takes an optional name parameter
# It uses the name to get a logger via logging.getLogger(name)
# The function doesn't actually call the logger methods, it just wraps them
# So we just need to pass a valid string name

ARGS = {
    "name": "test_logger"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lightning — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
configure_torch Not yet run
unverified (harvested, no recorded run)
ExplainableML/in-context-impersonation/src/utils/configure_torch.py
code served (permissive licence) · get_code("387e91e034d51983")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_pylogger 14 other papers
1 dated earlier, 1 the same month, 12 later · 1 only as an assembly brick
2209.03143 (2022-09)
AudioLM: a Language Modeling Approach to Audio Generation
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers
2310.01146 (2023-10)
NewsRecLib: A PyTorch-Lightning Library for Neural News Recommendation
and 11 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context. We ask LLMs to assume different personas before solving vision and language tasks. We do this by prefixing the prompt with a persona that is associated either with a social identity or domain expertise. In a multi-armed bandit task, we find that LLMs pretending to be children of different ages recover human-like developmental stages of exploration. In a language-based reasoning task, we find that LLMs impersonating domain experts perform better than LLMs impersonating non-domain experts. Finally, we test whether LLMs' impersonations are complementary to visual information when describing different categories. We find that impersonation can improve performance: an LLM prompted to be a bird expert describes birds better than one prompted to be a car expert. However, impersonation can also uncover LLMs' biases: an LLM prompted to be a man describes cars better than one prompted to be a woman. These findings demonstrate that LLMs are capable of taking on diverse roles and that this in-context impersonation can be used to uncover their strengths and hidden biases. Our code is available at https://github.com/ ExplainableML/in-context-impersonation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.14930")
get_code_for_paper("2305.14930")
have("2305.14930")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.14930.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.14930.svg)](https://syntology.ai/paper/2305.14930)

Connect an agent — have() is free.