README.md

---
library_name: transformers
license: odc-by
datasets:
- tceron/wildseek
language:
- en
metrics:
- f1
base_model:
- answerdotai/ModernBERT-large
pipeline_tag: text-classification
---

# Model Card for Model ID

This classifier classifier information seeking queries into 7 categories for high-risk sensitive queries. 

Labels: 

    0: "Other",
    1: "Economic and Financial",
    2: "Health",
    3: "Politics",
    4: "Judicial and Legal",
    5: "Moral Values and Religion",
    6: "Security",



## Model Details

All details in [paper](https://arxiv.org/abs/2608.30683): 
```bibtex
@inproceedings{ceron2026wildseek,
  title     = {WildSEEK: Evaluating Language Models for Information-Seeking},
  author    = {Ceron, Tanise and Baumann, Joachim and Bassignana, Elisa and Cabuk, Berat and Hovy, Dirk and Nozza, Debora},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year      = {2026}
}
```

## Other classifiers from this study are:
- **`tceron/info-seek-classifier`** — information seeking, content creation, coding, not english, no request
- **`tceron/open-endedness-classifier`** — Analytical, Factoid