Update README.md

add ethical considerations and limitations

README.md

@@ -620,7 +620,13 @@ Details coming soon.
 
 ## Ethical Considerations and Limitations
 
-Details coming soon.
+We examine the presence of undesired societal and cognitive biases present in this model using different benchmarks. For societal biases, we test performance using the BBQ dataset (Parrish et al., 2022) in the original English and the Regard dataset (Sheng et al., 2019). We report that moderate  accuracies (between 0.5 and 0.6 depending on the social groups) in disambiguated settings, the model performs very poorly in ambiguous setting. Taken together, these results suggest the pervasiveness of social biases that may have an effect on task performance
+
+Our cognitive bias analysis focuses on positional effects in 0-shot settings, and majority class bias in few-shot settings. For positional effects, we leverage the ARC Multiple Choice Question dataset (Clark et al., 2018). We observe significant, but moderate weak primacy effects, whereby the model shows a preference for answers towards the beginning of the list of provided answers. We measure effects of majority class effects in few-shot settings using SST-2 (Socher et al., 2013). We again detect significant effects, with a small effect size. This suggests that the model is relatively robust against the examined cognitive biases.
+
+We highlight that our analyses of these biases are by no means exhaustive and are limited by the relative scarcity of adequate resources in all languages present in the training data. We aim to gradually extend and expand our analyses in future work.
+
+These results can be expected from a model that has undergone only a preliminary instruction tuning. These tests are performed in order to show the biases the model may contain. We urge developers to take them into account and perform safety testing and tuning tailored to their specific applications of the model.
 
 ---