SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.20154 · EMNLP · 2025

Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?

Christine Largeron, Amine Trabelsi, Antoine Gourru, Anthony Dubreuil

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2510.20154.json · badge: /api/ran/2510.20154.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
slanglab/twitteraae canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
addAllnonempty Ran
ran; our contract draft was wrong, not the code
slanglab/twitteraae/code/twokenize.py
code served (permissive licence) · get_code("70a1c1f1b3951281")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch

torch.manual_seed(0)

master = []
smaller = ["  hello  ", "world", "   ", "", "test"]

ARGS = {
    "master": master,
    "smaller": smaller
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
splitEdgePunct Ran
ran; our contract draft was wrong, not the code
slanglab/twitteraae/code/twokenize.py
code served (permissive licence) · get_code("f6d36d824168d606")
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 str. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T01:20:17Z. 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 re

edgePunctChars = u'\'"""''«»{}\\(\\)\\[\\]\\*&'

edgePunct = '[' + edgePunctChars + ']'

notEdgePunct = '[a-zA-Z0-9]'

offEdge = '(^|$|:|;|\\s|\\.|,)'

EdgePunctLeft = re.compile(offEdge + '(' + edgePunct + '+)(' + notEdgePunct + ')', re.UNICODE)

EdgePunctRight = re.compile('(' + notEdgePunct + ')(' + edgePunct + '+)' + offEdge, re.UNICODE)

def splitEdgePunct(input):
    input = EdgePunctLeft.sub('\\1\\2 \\3', input)
    input = EdgePunctRight.sub('\\1 \\2\\3', input)
    return input

ARGS = {
    'input': 'Hello (world) and "friends"'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
infer_cvb0 Not yet run
unverified (harvested, no recorded run)
slanglab/twitteraae/code/predict.py
code served (permissive licence) · get_code("aad392706f25a6b6")
How it ran

no invocation recorded.

predict Not yet run
unverified (harvested, no recorded run)
slanglab/twitteraae/code/predict.py
code served (permissive licence) · get_code("5eab7b543c6a73d1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
addAllnonempty 1 other paper
1 dated earlier
2407.12710 (2024-07)
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
splitEdgePunct 1 other paper
1 dated earlier
2407.12710 (2024-07)
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems

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

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly, the evaluation of this kind of bias in stance detection methods has been largely overlooked by the community. Stance Detection involves labeling a statement as being against, in favor, or neutral towards a specific target and is among the most sensitive NLP tasks, as it often relates to political leanings. In this paper, we focus on the bias of Large Language Models when performing stance detection in a zero-shot setting. We automatically annotate posts in pre-existing stance detection datasets with two attributes: dialect or vernacular of a specific group and text complexity/readability, to investigate whether these attributes influence the model's stance detection decisions. Our results show that LLMs exhibit significant stereotypes in stance detection tasks, such as incorrectly associating pro-marijuana views with low text complexity and African American dialect with opposition to Donald Trump.

For agents

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

get_harvested_code_for_paper("2510.20154")
get_code_for_paper("2510.20154")
have("2510.20154")

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

curl https://syntology.ai/api/ran/2510.20154.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.20154.svg)](https://syntology.ai/paper/2510.20154)

Connect an agent — have() is free.