Evaluating Generative AI Systems is a Social Science Measurement Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916485623971840 |
|---|---|
| author | Wallach, Hanna Desai, Meera Pangakis, Nicholas Cooper, A. Feder Wang, Angelina Barocas, Solon Chouldechova, Alexandra Atalla, Chad Blodgett, Su Lin Corvi, Emily Dow, P. Alex Garcia-Gathright, Jean Olteanu, Alexandra Reed, Stefanie Sheng, Emily Vann, Dan Vaughan, Jennifer Wortman Vogel, Matthew Washington, Hannah Jacobs, Abigail Z. |
| author_facet | Wallach, Hanna Desai, Meera Pangakis, Nicholas Cooper, A. Feder Wang, Angelina Barocas, Solon Chouldechova, Alexandra Atalla, Chad Blodgett, Su Lin Corvi, Emily Dow, P. Alex Garcia-Gathright, Jean Olteanu, Alexandra Reed, Stefanie Sheng, Emily Vann, Dan Vaughan, Jennifer Wortman Vogel, Matthew Washington, Hannah Jacobs, Abigail Z. |
| contents | Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI (GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of measurement tasks found throughout the social sciences. With this in mind, we present a framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, impacts, opportunities, and risks of GenAI systems. The framework distinguishes between four levels: the background concept, the systematized concept, the measurement instrument(s), and the instance-level measurements themselves. This four-level approach differs from the way measurement is typically done in ML, where researchers and practitioners appear to jump straight from background concepts to measurement instruments, with little to no explicit systematization in between. As well as surfacing assumptions, thereby making it easier to understand exactly what the resulting measurements do and do not mean, this framework has two important implications for evaluating evaluations: First, it can enable stakeholders from different worlds to participate in conceptual debates, broadening the expertise involved in evaluating GenAI systems. Second, it brings rigor to operational debates by offering a set of lenses for interrogating the validity of measurement instruments and their resulting measurements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10939 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Generative AI Systems is a Social Science Measurement Challenge Wallach, Hanna Desai, Meera Pangakis, Nicholas Cooper, A. Feder Wang, Angelina Barocas, Solon Chouldechova, Alexandra Atalla, Chad Blodgett, Su Lin Corvi, Emily Dow, P. Alex Garcia-Gathright, Jean Olteanu, Alexandra Reed, Stefanie Sheng, Emily Vann, Dan Vaughan, Jennifer Wortman Vogel, Matthew Washington, Hannah Jacobs, Abigail Z. Computers and Society Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI (GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of measurement tasks found throughout the social sciences. With this in mind, we present a framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, impacts, opportunities, and risks of GenAI systems. The framework distinguishes between four levels: the background concept, the systematized concept, the measurement instrument(s), and the instance-level measurements themselves. This four-level approach differs from the way measurement is typically done in ML, where researchers and practitioners appear to jump straight from background concepts to measurement instruments, with little to no explicit systematization in between. As well as surfacing assumptions, thereby making it easier to understand exactly what the resulting measurements do and do not mean, this framework has two important implications for evaluating evaluations: First, it can enable stakeholders from different worlds to participate in conceptual debates, broadening the expertise involved in evaluating GenAI systems. Second, it brings rigor to operational debates by offering a set of lenses for interrogating the validity of measurement instruments and their resulting measurements. |
| title | Evaluating Generative AI Systems is a Social Science Measurement Challenge |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2411.10939 |