Skip to main content
. Author manuscript; available in PMC: 2023 Sep 6.
Published in final edited form as: Proc Conf Assoc Comput Linguist Meet. 2023 Jul;2023:15566–15589. doi: 10.18653/v1/2023.acl-long.868

Table 6:

Number of inaccurate false positives (FNs) and false negatives (FNs) identified during automated evaluation in GPT-3 labelled outputs under the in-context few-shot prompting setting.

Data Inaccure FPs / Total FPs Inaccurate FNs / Total FNs

ADE 108 / 209 136 / 417
CoNLL 92 / 183 56 / 152