_version_ 1866911735345053696
author Reuel, Anka
Ghosh, Avijit
Chim, Jenny
Tran, Andrew
Long, Yanan
Mickel, Jennifer
Gohar, Usman
Yadav, Srishti
Ammanamanchi, Pawan Sasanka
Allaham, Mowafak
Rahmani, Hossein A.
Akhtar, Mubashara
Friedrich, Felix
Scholz, Robert
Riegler, Michael Alexander
Batzner, Jan
Habba, Eliya
Saxena, Arushi
Kornilova, Anastassia
Wei, Kevin
Soni, Prajna
Mathew, Yohan
Klyman, Kevin
Sania, Jeba
Sahoo, Subramanyam
Bruvik, Olivia Beyer
Sadeghi, Pouya
Goswami, Sujata
Wang, Angelina
Jernite, Yacine
Talat, Zeerak
Biderman, Stella
Kochenderfer, Mykel
Koyejo, Sanmi
Solaiman, Irene
author_facet Reuel, Anka
Ghosh, Avijit
Chim, Jenny
Tran, Andrew
Long, Yanan
Mickel, Jennifer
Gohar, Usman
Yadav, Srishti
Ammanamanchi, Pawan Sasanka
Allaham, Mowafak
Rahmani, Hossein A.
Akhtar, Mubashara
Friedrich, Felix
Scholz, Robert
Riegler, Michael Alexander
Batzner, Jan
Habba, Eliya
Saxena, Arushi
Kornilova, Anastassia
Wei, Kevin
Soni, Prajna
Mathew, Yohan
Klyman, Kevin
Sania, Jeba
Sahoo, Subramanyam
Bruvik, Olivia Beyer
Sadeghi, Pouya
Goswami, Sujata
Wang, Angelina
Jernite, Yacine
Talat, Zeerak
Biderman, Stella
Kochenderfer, Mykel
Koyejo, Sanmi
Solaiman, Irene
contents Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor remain uneven. To characterize this landscape, we conduct the first comprehensive analysis of social impact evaluation reporting, examining 186 first-party release reports and 248 third-party evaluation sources, supplemented by developer interviews. We find a stark division of labor: first-party reporting is sparse, often superficial, and declining in areas like environmental impact and bias, while third-party evaluators provide broader, more rigorous coverage of bias, harmful content, and performance disparities. However, only developers can authoritatively report on data provenance, content moderation labor, costs, and infrastructure, yet interviews reveal these disclosures are deprioritized unless tied to product adoption or compliance. Current practices leave major gaps in assessing societal impacts, underscoring the need for policies that mandate developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure for aggregating third-party evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05613
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
Reuel, Anka
Ghosh, Avijit
Chim, Jenny
Tran, Andrew
Long, Yanan
Mickel, Jennifer
Gohar, Usman
Yadav, Srishti
Ammanamanchi, Pawan Sasanka
Allaham, Mowafak
Rahmani, Hossein A.
Akhtar, Mubashara
Friedrich, Felix
Scholz, Robert
Riegler, Michael Alexander
Batzner, Jan
Habba, Eliya
Saxena, Arushi
Kornilova, Anastassia
Wei, Kevin
Soni, Prajna
Mathew, Yohan
Klyman, Kevin
Sania, Jeba
Sahoo, Subramanyam
Bruvik, Olivia Beyer
Sadeghi, Pouya
Goswami, Sujata
Wang, Angelina
Jernite, Yacine
Talat, Zeerak
Biderman, Stella
Kochenderfer, Mykel
Koyejo, Sanmi
Solaiman, Irene
Computers and Society
Artificial Intelligence
Machine Learning
Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor remain uneven. To characterize this landscape, we conduct the first comprehensive analysis of social impact evaluation reporting, examining 186 first-party release reports and 248 third-party evaluation sources, supplemented by developer interviews. We find a stark division of labor: first-party reporting is sparse, often superficial, and declining in areas like environmental impact and bias, while third-party evaluators provide broader, more rigorous coverage of bias, harmful content, and performance disparities. However, only developers can authoritatively report on data provenance, content moderation labor, costs, and infrastructure, yet interviews reveal these disclosures are deprioritized unless tied to product adoption or compliance. Current practices leave major gaps in assessing societal impacts, underscoring the need for policies that mandate developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure for aggregating third-party evaluations.
title Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
topic Computers and Society
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.05613