Update Readme

README.md

@@ -3,11 +3,14 @@ license: llama2
 language:
 - en
 ---
-# DAMA 7B
+# DAMA 
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-## Model Details
+## Model 
+
+LLaMA model adapted to mitigate gender bias in text generation.
+For adaptation, we used **D**ebiasing **A**lgorithm through **M**odel **A**daptation (DAMA) method described in [Limisiewicz et al., 2024](https://openreview.net/pdf?id=XIZEFyVGC9).
 
 ### Model Description
 
@@ -16,35 +19,105 @@ language:
 
 
 - **Developed by:** Tomasz Limisiewicz, David Mareček, Tomáš Musil
+- **Funded by:** Grant Agency Czech Republic
 - **Language(s) (NLP):** English
-- **Adapted from model:** LLaMA 7B
+- **Adapted from model:** LLaMA
+
+### Model Sizes
+
+- **[7B](https://huggingface.co/ufal/DAMA-7B)**
+- **[13B](https://huggingface.co/ufal/DAMA-13B)**
+- **[33B](https://huggingface.co/ufal/DAMA-33B)**
+- **[65B](https://huggingface.co/ufal/DAMA-65B)**
 
 ### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [Link](github.com/tomlimi/DAMA)
-- **Paper:** [Link](openreview.net/pdf?id=XIZEFyVGC9)
+- **[Repository](github.com/tomlimi/DAMA)** 
+- **[Paper](openreview.net/pdf?id=XIZEFyVGC9)**
 
-## 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
+## Bias, Risks, and Limitations
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-The model is the adapted version of LLaMA 7B for decreasing gender bias.
+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. 
 
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## Adaptation
 
-The model mitigates the gender bias of the original model. 
-Thus, it is better suited for the generation and processing of texts in sensitive domains.
+<!-- Include image. -->
+
+![Dama Schema](DamaSchema.png)
+
+Schema (b) shows DAMA intervention in a LLaMA layer.
+Even though `I - P_c` is depicted as a separate module, in practice, it is multiplied with the output matrix of a feed-forward layer (`W_FF`).
+Therefore, DAMA is neutral to the model's parameter count and architecture.
+(a) We show the behavior of the model when presented with a stereotypical prompt.
+Specifically, (c) shows the projections of the feed-forward latent vector (`u`) onto the output space.
+With DAMA (lower arrow), we nullify the gender component of the representation. 
+It results in balanced probabilities of gendered tokens in the model's output, as shown in (d).
+
+The method for obtaining `P_c` is based on the Partial Least Square algorithm.
+For more details, please refer to the [paper](https://openreview.net/pdf?id=XIZEFyVGC9).
+
+## Evaluation
+
+We evaluate the models on multiple benchmarks to assess gender bias and language understanding capabilities.
+DAMA models are compared with the original LLaMA models.
 
 
+### Bias Evaluation
+
+We introduced a metric for evaluating gender bias in text generation.
+It measures to which extent the models' output is affected by stereotypical `a_s` and factual `a_f` gender signals.
+
+Moreover, we provide the scores for two established bias benchmarks: **WinoBias** and **Stereoset**.
+
+### Results
+
+
+|                                                                    | 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 |
+| DAMA 7B                                                            | -0.005 | 0.038 | -0.006 | 57.3\% | 31.5\%    | 2.3\%     | 95.5 | 69.3      | 58.5 |
+| LLaMA 13B                                                          | 0.270  | 0.351 | 0.070  | 70.5\% | 35.7\%    | -1.5\%    | 95.2 | 71.4      | 54.4 |
+| DAMA 13B                                                           | 0.148  | 0.222 | 0.059  | 66.4\% | 31.1\%    | -1.1\%    | 94.4 | 68.6      | 59.4 |
+| LLaMA 33B                                                          | 0.265  | 0.343 | 0.092  | 71.0\% | 36.0\%    | -4.0\%    | 94.7 | 68.4      | 59.9 |
+| 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. |        |       |        |        |           |           |      |           |      |
+
+
+### Performance Evaluation
+
+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**.
+
+
+### Results
+
+|           | Perpelexity    | ARC-C | ARC-E |OBQA  | MMLU  |
+|-----------|----------------|----------------|-----------|-----------------|-------|
+| LLaMA 7B  | 26.1       | 42.2           |69.1       | 57.2            | 30.3  |
+| DAMA 7B   | 28.9           | 41.8           | 68.3      | 56.2            | 30.8  |
+| LLaMA 13B | 19.8           | 44.9           | 70.6      | 55.4            | 43.3  |
+| DAMA 13B  | 21.0           | 44.7           | 70.3      | 56.2            | 43.5  |
+| LLaMA 33B | 20.5           | 47.4 | 72.9      | 59.2            | 55.7* |
+| DAMA 33B  | 19.6           | 45.2           | 71.6      | 58.2            | 56.1* |
+| 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.
+Due to hardware limitations, we could not run MMLU inference for 65B models.
+In the evaluation of 33B model, we excluded 4\% longest prompts.
 
 ## Citation
 
@@ -62,3 +135,7 @@ year={2024},
 url={https://openreview.net/forum?id=XIZEFyVGC9}
 }
 ```
+
+## Model Card Author
+
+[Tomasz Limisiewicz](mailto:limisewicz@ufal.mff.cuni.cz)