AI-Assisted Systematization for Evaluating GenAI Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911716674109440 |
|---|---|
| author | Agarwal, Dhruv Sheng, Emily Atalla, Chad Garcia-Gathright, Jean Mozannar, Hussein Washington, Hannah Chouldechova, Alexandra Barocas, Solon Wallach, Hanna |
| author_facet | Agarwal, Dhruv Sheng, Emily Atalla, Chad Garcia-Gathright, Jean Mozannar, Hussein Washington, Hannah Chouldechova, Alexandra Barocas, Solon Wallach, Hanna |
| contents | Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When these concepts are left underspecified, it becomes unclear what should be measured or how evaluation results should be interpreted. This problem reflects a missing step: systematization, that is, moving from a broad background concept to an explicit, structured account of the concept in measurable terms. To help address the fact that systematization is cognitively demanding and resource-intensive, we investigate whether AI assistance can support this process. To enable AI-assisted systematization and assess its quality, we introduce a structured representation of a systematized concept, a concept spec, and a validation worksheet. We then develop two AI-assisted systematizers: a direct, zero-shot approach and a multi-agent approach that more closely mirrors manual systematization approaches from existing literature. We use these systematizers to produce concept specs for two concepts -- hate-based rhetoric and digital empathy -- and evaluate resulting concept specs on content validity and information recoverability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26001 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AI-Assisted Systematization for Evaluating GenAI Systems Agarwal, Dhruv Sheng, Emily Atalla, Chad Garcia-Gathright, Jean Mozannar, Hussein Washington, Hannah Chouldechova, Alexandra Barocas, Solon Wallach, Hanna Computation and Language Artificial Intelligence Computers and Society Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When these concepts are left underspecified, it becomes unclear what should be measured or how evaluation results should be interpreted. This problem reflects a missing step: systematization, that is, moving from a broad background concept to an explicit, structured account of the concept in measurable terms. To help address the fact that systematization is cognitively demanding and resource-intensive, we investigate whether AI assistance can support this process. To enable AI-assisted systematization and assess its quality, we introduce a structured representation of a systematized concept, a concept spec, and a validation worksheet. We then develop two AI-assisted systematizers: a direct, zero-shot approach and a multi-agent approach that more closely mirrors manual systematization approaches from existing literature. We use these systematizers to produce concept specs for two concepts -- hate-based rhetoric and digital empathy -- and evaluate resulting concept specs on content validity and information recoverability. |
| title | AI-Assisted Systematization for Evaluating GenAI Systems |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2605.26001 |