biankasimkova/qwen3-8b-finetuned-court-decisions-sk-appeal-success-classifier

Model Card: Appeal Success Prediction

Model Description

This model is a fine-tuned version of biankasimkova/qwen3-8b-finetuned-court-decisions-sk-v1 for binary classification of Slovak court decisions. Given the text of a court decision, the model predicts whether an appeal against that decision is likely to succeed.

• —Developed by: Bianka Šimková
• —Model type: Causal LLM fine-tuned for sequence classification
• —Language: Slovak
• —License: Apache license 2.0
• —Base model: biankasimkova/qwen3-8b-finetuned-court-decisions-sk-v1
• —Fine-tuned for: Diploma thesis — Using large language models for analyzing decisions of Slovak courts

Intended Use

Primary Use

Predicting whether an appeal against a Slovak court decision will succeed (binary classification: 0 = appeal fails, 1 = appeal succeeds).

Out-of-Scope Use

• —Court decisions in languages other than Slovak
• —Legal advice or real-world legal decision support — this model is a research prototype and should not be used for any actual legal proceedings

Training Data

The training data consists of Slovak court decisions sourced from open government records of the Slovak Republic. The dataset was preprocessed and split into logical sections (introduction, statement, reasoning) as part of the thesis pipeline.

• —Data source: Open data portal of the Slovak Republic
• —Dataset format: JSON
• —Preprocessing: Text cleaning, segmentation into logical parts, sampling of examples under 3000 tokens

Training Procedure

• —Base model: biankasimkova/qwen3-8b-finetuned-court-decisions-sk-v1
• —Fine-tuning method: LoRA
• —Framework: Hugging Face Transformers
• —Hardware: NVIDIA RTX A6000
• —Epochs: 3
• —Batch size: 1

Evaluation Results

Labels

Limitations

• —Trained on Slovak court decisions only; performance on other legal systems or languages is not guaranteed
• —The model reflects patterns in historical court data, which may contain biases
• —Not intended for production legal use

Citation

If you use this model, please cite the associated thesis:

@mastersthesis{Simkova2026,
  author    = {Bianka Šimková},
  title     = {Using large language models for analyzing decisions of Slovak courts},
  school    = {Institute of Artificial Intelligence,
Faculty of Electrical Engineering and Informatics, 
Technical University of Košice},
  year      = {2026}
}