Xlm Roberta Mushroom Qa

🚀 xlm-roberta-mushroom-qa

This model, xlm-roberta-mushroom-qa, was fine - tuned to address SemEval 2025 Task3: Mu - SHROOM. Its main task is to extract hallucination spans from large language model output, offering a solution for handling specific language - related tasks.

🚀 Quick Start

This section provides a high - level overview of the model. The xlm - roberta - mushroom - qa model is designed to solve the problem of extracting hallucination spans from large language model output, which is a significant task in the field of natural language processing.

📚 Documentation

Model description

The model xlm - roberta - mushroom - qa was fine - tuned for SemEval 2025 Task3: Mu - SHROOM. However, more detailed information about the model's architecture, design philosophy, and unique features is yet to be provided.

Intended uses & limitations

As of now, while we know the model is for extracting hallucination spans from large language model output, comprehensive information regarding its intended usage scenarios, potential limitations in different contexts, and edge - case handling is still required.

Training and evaluation data

Details about the training and evaluation data, such as the data sources, data pre - processing steps, data distribution, and the characteristics of the evaluation dataset, are not available at present.

🔧 Technical Details

Training procedure

Fine - tuning hyperparameters

The following hyperparameters were used during the fine - tuning process:

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0