Sami92
/

XLM-R-Large-Disinfo-Narrative-Classifier

@@ -5,67 +5,19 @@ tags: []
 # Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
 ## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 [More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 ## How to Get Started with the Model
@@ -81,119 +33,48 @@ Use the code below to get started with the model.
 [More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
 #### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
 ## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
 [More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
 ### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 # Model Card for Model ID
+This model is a fine-tuned version of [XLM-R Large](https://huggingface.co/FacebookAI/xlm-roberta-large). It is trained to classify common disinformation narratives, a task that is important to automated fact-checking. It was trained in a weakly-supervised fashion using GPT-4o. The datasets are German, however, the underlying model is multilingual. It was not tested how the model performs in other languages. For testing a sample of fact-checks from German fact-checking organizations was inspected and if the checked claim supported one of the narratives, the social media posts with the original text were extracted.
 ## Model Details
 ## Bias, Risks, and Limitations
 [More Information Needed]
 ## How to Get Started with the Model
 [More Information Needed]
 #### Training Hyperparameters
+- Epochs: 10
+- Batch size: 16
+- learning_rate: 2e-5
+- weight_decay: 0.01
+- fp16: True
 ## Evaluation
+### Testing Data
 [More Information Needed]
 ### Results
+| Category                                                                                                                     | Precision | Recall | F1-Score | Support |
+|------------------------------------------------------------------------------------------------------------------------------|:---------:|:------:|:--------:|:-------:|
+| 5G verursacht Krankheiten für Menschen und Tiere.                                                                            |   1.00    |  0.83  |   0.91   |    6    |
+| Ausländer sind krimineller als Deutsche, werden geringer bestraft und begehen mehr Straftaten, und das wird uns verheimlicht. |   1.00    |  0.67  |   0.80   |    3    |
+| Ausländer und Migranten bekommen mehr Leistungen oder Wohnungen vom Staat als Deutsche.                                      |   1.00    |  1.00  |   1.00   |    9    |
+| Bargeld soll abgeschafft werden.                                                                                             |   0.67    |  1.00  |   0.80   |    2    |
+| Das Wetter war früher überhaupt nicht anders und Naturphänomene wie Vulkanausbrüche sind schuld am Klimawandel.              |   1.00    |  1.00  |   1.00   |    7    |
+| Der Anteil des Menschen an den Treibhausgasen ist nur gering und die Wahrheit über den Klimawandel wird verheimlicht.        |   1.00    |  1.00  |   1.00   |    7    |
+| Der WHO-Pandemievertrag hebt die Souveränität von Staaten auf und führt zu einer WHO-Diktatur.                               |   1.00    |  1.00  |   1.00   |    1    |
+| Der Westen hat ein Friedensabkommen zwischen Russland und der Ukraine verhindert.                                            |   0.00    |  0.00  |   0.00   |    0    |
+| Deutschland wird von Faschisten regiert.                                                                                     |   1.00    |  1.00  |   1.00   |    1    |
+| Die Covid-19-Impfung ist nicht ausreichend erforscht und verursacht Nebenwirkungen.                                          |   0.91    |  0.83  |   0.87   |   12    |
+| Die Regierung will gezielt Migranten ins Land holen und schickt Geld ins Ausland während unsere Leute leiden.                |   0.67    |  1.00  |   0.80   |    2    |
+| Die Stimmzettel, Urnen und Briefwahl sind manipuliert und Wahlhelfer lassen Stimmen verschwinden.                            |   1.00    |  1.00  |   1.00   |   16    |
+| Die Wahrheit über die Corona-Maßnahmen, Todesopfer und Covid-Impfung wird verheimlicht.                                      |   0.75    |  1.00  |   0.86   |    3    |
+| E-Mobilität ist schlechter für die Umwelt als Verbrenner Autos.                                                              |   1.00    |  1.00  |   1.00   |    2    |
+| Gewisse Lebensmittel, Leitungswasser oder Gentechnik sind gesundheitsschädlich und machen unfruchtbar.                       |   1.00    |  1.00  |   1.00   |   10    |
+| Hilfsgüter an die Ukraine werden in Wahrheit weggeworfen oder zerstört.                                                      |   1.00    |  1.00  |   1.00   |    3    |
+| Keins der Narrative trifft zu.                                                                                               |   0.00    |  0.00  |   0.00   |    0    |
+| Selensky ist korrupt und drogenabhängig und die Ukraine wird von Nazis regiert.                                              |   1.00    |  0.33  |   0.50   |    3    |
+| Windräder töten hunderttausende Vögel, verursachen Luftwirbel und Dürre und es werden Wälder für die Windräder gerohdet.     |   1.00    |  1.00  |   1.00   |    9    |
+| **Accuracy**                                                                                                                 |           |        |   0.94   |   96    |
+| **Macro avg**                                                                                                                |   0.84    |  0.82  |   0.82   |   96    |
+| **Weighted avg**                                                                                                             |   0.97    |  0.94  |   0.94   |   96    |