all-mpnet-base-v2_noneconomic-attributes-classifier

Group mention non-economic attributes classifier

A multi-label classifier for detecting non-economic attribute categories referred to in a social group mention, trained with setfit based on the light-weight sentence-transformers/all-mpnet-base-v2 sentence embedding model.

The non-economic attributes classified are:

Model Details

Model Description

Group mention non-economic attributes classifier

• Developed by: Hauke Licht, Leonce Röth
• Model type: mpnet
• Language(s) (NLP): ['en']
• License: apache-2.0
• Finetuned from model: sentence-transformers/all-mpnet-base-v2
• Funded by: The Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy – EXC 2126/1 – 390838866

Model Sources

• Repository: GitHub
• Paper: Journal of European Public Policy

Uses

Bias, Risks, and Limitations

• Evaluation of the classifier on held-out data shows that it makes mistakes.
• The model has been fine-tuned only on human-annotated social group mentions recorded in sentences sampled from party manifestos of European parties (mostly far-right and Green parties). Applying the classifier in other domains can lead to higher error rates.
• The data used to fine-tune the model comes from human annotators. Human annotators can be biased, and factors like gender and social background can impact their annotation judgments. This may lead to bias in the detection of specific social groups.

Recommendations

• Users who want to apply the model outside its training data domain should evaluate its performance in the target data.
• Users who want to apply the model outside its training data domain should continue to fine-tune this model on labeled data.

How to Get Started with the Model

Use the code below to get started with the model.

Usage

You can use the model with the setfit Python library (>=1.1.0):

Note: It is recommended to use transformers version >=4.5.5,<=5.0.0 and sentence-transformers version >=4.0.1,<=5.1.0 for compatibility.

Classification

import torch
from setfit import SetFitModel

model_name = "haukelicht/all-mpnet-base-v2_noneconomic-attributes-classifier"
device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
classifier = SetFitModel.from_pretrained(model_name)
classifier.to(device);

# Example mentions
mentions = ["working class people", "highly-educated professionals", "people without a stable job"]

# Get predictions
with torch.no_grad():
    predictions = classifier.predict(mentions)
print(predictions)

# Map predictions to labels
[
    [
        classifier.id2label[l]
        for l, p in enumerate(pred) if p==1
    ]
    for pred in predictions
]

Mention embedding

import torch
from sentence_transformers import SentenceTransformer

model_name = "haukelicht/all-mpnet-base-v2_noneconomic-attributes-classifier"
device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"

# Load the sentence transformer component of the pre-trained classifier
model = SentenceTransformer(model_name, device=device)

# Example mentions
mentions = ["working class people", "highly-educated professionals", "people without a stable job"]

# Compute mention embeddings
with torch.no_grad():
    embeddings = model.encode(mentions)

Training Details

Training Data

The train, dev, and test splits used for model fine-tuning and evaluation are available on GitHub.

Training Procedure

Training Hyperparameters

• num epochs: (1, 6)
• train batch sizes: (32, 4)
• body train max steps: 300
• head learning rate: 0.010
• L2 weight: 0.01
• warmup proportion: 0.15

Evaluation

Testing Data, Factors & Metrics

Testing Data

The train, dev, and test splits used for model fine-tuning and evaluation are available on GitHub.

Citation

BibTeX:

@article{licht_roeth_2026,
  title={Attributes, abstractions, and combinations: a new taxonomy for studying how parties invoke social groups},
  author={Hauke Licht and Leonce Röth},
  journal={Journal of European Public Policy},
  volume={},
  number={},
  pages={1–40},
  year={2026},
  date={2026-10-01},
  url={http://www.tandfonline.com/10.1080/13501763.2026.2737691},
  doi={10.1080/13501763.2026.2737691}
}

APA:

Licht, H., & Röth, L. (2026). Attributes, abstractions, and combinations: a new taxonomy for studying how parties invoke social groups. Journal of European Public Policy, 1–40. https://doi.org/10.1080/13501763.2026.2737691

Model Card Contact

[email protected]