thu-coai/SeTox-Qwen2.5-7B

SeTox-Qwen2.5-7B

SeTox-Qwen2.5-7B is a full-SFT model based on Qwen/Qwen2.5-7B-Instruct for Chinese neologism toxicity detection with optional web-search tool use.

Training

• —Base model: Qwen/Qwen2.5-7B-Instruct
• —Method: full supervised fine-tuning
• —Training data: SeTox tool-use and direct SFT data
• —Epochs: 4
• —Learning rate: 1e-5
• —Scheduler: linear with warmup ratio 0.05
• —Context cutoff: 4096

Evaluation

Main SeTox neologism test set, 624 valid samples:

Live search and generation settings can introduce small drift during reproduction.

Usage

See the SeTox code repository for search-augmented inference:

python scripts/run_inference.py \
  --model_path thu-coai/SeTox-Qwen2.5-7B \
  --search_backend serper \
  --input_path data/eval/neologism_test.json \
  --output_path outputs/neologism_predictions.json

For offline smoke tests, use --mock or --search_backend none.

Limitations

This model is intended for research on Chinese neologism toxicity detection. It can make mistakes on ambiguous, fast-changing, adversarial, or under-specified terms. Search results may contain noisy or unsafe snippets, and downstream users should apply appropriate safety review before deployment.

License

This model is fine-tuned from Qwen/Qwen2.5-7B-Instruct and follows the Apache-2.0 license inherited from the base model.

Citation

Please cite the SeTox ACL paper:

• —Paper: https://aclanthology.org/2026.acl-long.1602/
• —DOI: https://doi.org/10.18653/v1/2026.acl-long.1602

@inproceedings{cui-etal-2026-setox,
  title = "{S}e{T}ox: Search-enhanced Reasoning for {LLM}-based Toxicity Detection over {C}hinese Internet Buzzwords",
  author = "Cui, Yiming and Zhang, Qinglin and Su, Xu and Min, Changyu and Hu, Shilin and Huang, Minlie",
  editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher",
  booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
  month = jul,
  year = "2026",
  address = "San Diego, California, USA",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2026.acl-long.1602/",
  doi = "10.18653/v1/2026.acl-long.1602",
  pages = "33018--33034"
}