Papers by Wolf Tilo Balke
Quantifying Bias from Decoding Techniques in Natural Language Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Natural language generation (NLG) models can propagate social bias towards particular demography. |
| Approach: | They propose to examine whether bias metrics like toxicity and sentiment are impacted by decoding techniques that use stochastic decoding. |
| Outcome: | The proposed methods reveal the imperative of testing inference time bias and provide evidence on the usefulness of inspecting the entire decoding spectrum. |