Update README.md

README.md

@@ -2,6 +2,16 @@
 license: llama2
 language:
 - en
+datasets:
+- McGill-NLP/stereoset
+- wino_bias
+- wikitext
+- allenai/ai2_arc
+- allenai/openbookqa
+- cais/mmlu
+metrics:
+- perplexity
+- accuracy
 ---
 # DAMA 
 
@@ -19,7 +29,7 @@ For adaptation, we used **D**ebiasing **A**lgorithm through **M**odel **A**dapta
 
 
 - **Developed by:** Tomasz Limisiewicz, David Mareček, Tomáš Musil
-- **Funded by:** Grant Agency Czech Republic
+- **Funded by:** Grant Agency of Czech Republic
 - **Language(s) (NLP):** English
 - **Adapted from model:** LLaMA
 
@@ -43,9 +53,9 @@ For adaptation, we used **D**ebiasing **A**lgorithm through **M**odel **A**dapta
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-The model mitigates the gender bias of the original model. 
-It is better suited for generating and processing texts in sensitive domains.
-However, we recommend caution for such use cases because the models retain bias. 
+DAMA mitigates the gender bias of the original model. 
+It is better suited for generating and processing texts in sensitive domains, such as hiring, social services, or professional counseling.
+Still, we recommend caution for such use cases because bias is not entirely erased (the same as in any other currently available method).
 
 
 
@@ -82,7 +92,7 @@ Moreover, we provide the scores for two established bias benchmarks: **WinoBias*
 ### Results
 
 
-|                                                                    | Bias   | in    | LM     |        | WinoBias  |           |      | StereoSet |      |
+||  Bias in LM ||| WinoBias  ||| Stereoset |||    
 |--------------------------------------------------------------------|--------|-------|--------|--------|-----------|-----------|------|-----------|------|
 |                                                                    | `a_s`  | `a_f` | `b`    | Acc    | `Delta S` | `Delta G` | lms  | ss        | ICAT |
 | LLaMA 7B                                                           | 0.235  | 0.320 | 0.072  | 59.1\% | 40.3\%    | 3.0\%     | 95.5 | 71.9      | 53.7 |
@@ -93,12 +103,13 @@ Moreover, we provide the scores for two established bias benchmarks: **WinoBias*
 | DAMA  33B                                                          | 0.105  | 0.172 | 0.059  | 63.7\% | 26.7\%    | -3.7\%    | 94.8 | 65.7      | 65.0 |
 | LLaMA 65B                                                          | 0.249  | 0.316 | 0.095  | 73.3\% | 35.7\%    | 1.4\%     | 94.9 | 69.5      | 57.9 |
 | DAMA  65B                                                          | 0.185  | 0.251 | 0.100  | 71.1\% | 27.2\%    | 0.8\%     | 92.8 | 67.1      | 61.1 |
-| Bias evaluation for the LLaMA models and their debiased instances. |        |       |        |        |           |           |      |           |      |
+
+Bias evaluation for the LLaMA models and their debiased instances.
 
 
 ### Performance Evaluation
 
-To check the effect of debiasing on LM capabilities, we compute perplexity on Wikipedia corpus.
+To check the effect of debiasing on LM capabilities, we compute perplexity on **Wikipedia corpus**.
 We also test performance on four language understanding end-tasks: **OpenBookQA**, **AI2 Reasoning Challenge** (Easy and Chalange Sets), and **Massive Multitask Language Understanding**.
 
 
@@ -115,7 +126,7 @@ We also test performance on four language understanding end-tasks: **OpenBookQA*
 | LLaMA 65B | 19.5 | 44.5           | 73.9 | 59.6 | ---*  |
 | DAMA 65B  | 20.1           | 40.5           | 67.7      | 57.2            | --- * |
 
-Performance evaluation for the \llama{} models and their debiased instances.
+Performance evaluation for the LLaMA models and their debiased instances.
 Due to hardware limitations, we could not run MMLU inference for 65B models.
 In the evaluation of 33B model, we excluded 4\% longest prompts.
 
@@ -123,9 +134,10 @@ In the evaluation of 33B model, we excluded 4\% longest prompts.
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
+
 **BibTeX:**
 
-```
+```bibtex
 @inproceedings{
 limisiewicz2024debiasing,
 title={Debiasing Algorithm through Model Adaptation},
@@ -136,6 +148,11 @@ url={https://openreview.net/forum?id=XIZEFyVGC9}
 }
 ```
 
+**APA:**
+
+Limisiewicz, T., Mareček, D., & Musil, T. (2024). Debiasing Algorithm through Model Adaptation. The Twelfth International Conference on Learning Representations.
+
+
 ## Model Card Author
 
 [Tomasz Limisiewicz](mailto:limisewicz@ufal.mff.cuni.cz)