mario-mgmn
commited on
Commit
•
c46c980
1
Parent(s):
e722480
Update README.md
Browse filesAdd ethical considerations and limitations
README.md
CHANGED
@@ -551,7 +551,13 @@ Details coming soon.
|
|
551 |
|
552 |
## Ethical Considerations and Limitations
|
553 |
|
554 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
555 |
|
556 |
---
|
557 |
|
|
|
551 |
|
552 |
## Ethical Considerations and Limitations
|
553 |
|
554 |
+
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 inadequate accuracies in both ambiguous and disambiguated contexts, which is indicative of the presence of societal biases which need to be addressed in post-training phases.
|
555 |
+
|
556 |
+
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 moderate to strong to very strong 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 detect moderate effects, implying that outputs can be influenced by the prompts.
|
557 |
+
|
558 |
+
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.
|
559 |
+
|
560 |
+
We highlight that these results can be expected from a pretrained model that has not yet been instruction-tuned or aligned. 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.
|
561 |
|
562 |
---
|
563 |
|