Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.03291 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913574683672576 |
|---|---|
| author | Liu, Weitang Li, Ying Wai Li, Yuelei Wang, Zihan You, Yi-Zhuang Shang, Jingbo |
| author_facet | Liu, Weitang Li, Ying Wai Li, Yuelei Wang, Zihan You, Yi-Zhuang Shang, Jingbo |
| contents | Evaluating models on datasets often fails to capture their behavior when faced with unexpected and diverse types of inputs. It would be beneficial if we could evaluate the difference between human annotation and model prediction for an internet number of inputs, or more generally, for an input space that enumeration is computationally impractical. Traditional model evaluation methods rely on precision and recall (PR) as metrics, which are typically estimated by comparing human annotations with model predictions on a specific dataset. This is feasible because enumerating thousands of test inputs is manageable. However, estimating PR across a large input space is challenging because enumeration becomes computationally infeasible. We propose OmniInput, a novel approach to evaluate and compare NNs by the PR of an input space. OmniInput is distinctive from previous works as its estimated PR reflects the estimation of the differences between human annotation and model prediction in the input space which is usually too huge to be enumerated. We empirically validate our method within an enumerable input space, and our experiments demonstrate that OmniInput can effectively estimate and compare precision and recall for (large) language models within a broad input space that is not enumerable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_03291 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Evaluation of human-model prediction difference on the Internet Scale of Data Liu, Weitang Li, Ying Wai Li, Yuelei Wang, Zihan You, Yi-Zhuang Shang, Jingbo Machine Learning Artificial Intelligence Evaluating models on datasets often fails to capture their behavior when faced with unexpected and diverse types of inputs. It would be beneficial if we could evaluate the difference between human annotation and model prediction for an internet number of inputs, or more generally, for an input space that enumeration is computationally impractical. Traditional model evaluation methods rely on precision and recall (PR) as metrics, which are typically estimated by comparing human annotations with model predictions on a specific dataset. This is feasible because enumerating thousands of test inputs is manageable. However, estimating PR across a large input space is challenging because enumeration becomes computationally infeasible. We propose OmniInput, a novel approach to evaluate and compare NNs by the PR of an input space. OmniInput is distinctive from previous works as its estimated PR reflects the estimation of the differences between human annotation and model prediction in the input space which is usually too huge to be enumerated. We empirically validate our method within an enumerable input space, and our experiments demonstrate that OmniInput can effectively estimate and compare precision and recall for (large) language models within a broad input space that is not enumerable. |
| title | Evaluation of human-model prediction difference on the Internet Scale of Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2312.03291 |