Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

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 practices remain uneven across the AI ecosystem. To characterize this landscape, we conduct the first comprehensive analysis of both first-party and third-party social impact evaluation reporting across a wide range of model developers. Our study examines 186 first-party release reports and 183 post-release evaluation sources, and complements this quantitative analysis with interviews of model developers. We find a clear division of evaluation labor: first-party reporting is sparse, often superficial, and has declined over time in key areas such as environmental impact and bias, while third-party evaluators including academic researchers, nonprofits, and independent organizations provide broader and more rigorous coverage of bias, harmful content, and performance disparities. However, this complementarity has limits. Only model developers can authoritatively report on data provenance, content moderation labor, financial costs, and training infrastructure, yet interviews reveal that these disclosures are often deprioritized unless tied to product adoption or regulatory compliance. Our findings indicate that current evaluation practices leave major gaps in assessing AI's societal impacts, highlighting the urgent need for policies that promote developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure to aggregate and compare third-party evaluations in a consistent and accessible way.

An Item Response Theory Framework for Persuasion

In this paper, we apply Item Response Theory, popular in education and political science research, to the analysis of argument persuasiveness in language. We empirically evaluate the model's performance on three datasets, including a novel dataset in the area of political advocacy. We show the advantages of separating these components under several style and content representations, including evaluating the ability of the speaker embeddings generated by the model to parallel real-world observations about persuadability.

BillSum: A Corpus for Automatic Summarization of US Legislation

Automatic summarization methods have been studied on a variety of domains, including news and scientific articles. Yet, legislation has not previously been considered for this task, despite US Congress and state governments releasing tens of thousands of bills every year. In this paper, we introduce BillSum, the first dataset for summarization of US Congressional and California state bills (https://github.com/FiscalNote/BillSum). We explain the properties of the dataset that make it more challenging to process than other domains. Then, we benchmark extractive methods that consider neural sentence representations and traditional contextual features. Finally, we demonstrate that models built on Congressional bills can be used to summarize California bills, thus, showing that methods developed on this dataset can transfer to states without human-written summaries.

How Predictable is Your State? Leveraging Lexical and Contextual Information for Predicting Legislative Floor Action at the State Level

Modeling U.S. Congressional legislation and roll-call votes has received significant attention in previous literature. However, while legislators across 50 state governments and D.C. propose over 100,000 bills each year, and on average enact over 30% of them, state level analysis has received relatively less attention due in part to the difficulty in obtaining the necessary data. Since each state legislature is guided by their own procedures, politics and issues, however, it is difficult to qualitatively asses the factors that affect the likelihood of a legislative initiative succeeding. Herein, we present several methods for modeling the likelihood of a bill receiving floor action across all 50 states and D.C. We utilize the lexical content of over 1 million bills, along with contextual legislature and legislator derived features to build our predictive models, allowing a comparison of the factors that are important to the lawmaking process. Furthermore, we show that these signals hold complementary predictive power, together achieving an average improvement in accuracy of 18% over state specific baselines.

Party Matters: Enhancing Legislative Embeddings with Author Attributes for Vote Prediction

Predicting how Congressional legislators will vote is important for understanding their past and future behavior. However, previous work on roll-call prediction has been limited to single session settings, thus did not consider generalization across sessions. In this paper, we show that metadata is crucial for modeling voting outcomes in new contexts, as changes between sessions lead to changes in the underlying data generation process. We show how augmenting bill text with the sponsors' ideologies in a neural network model can achieve an average of a 4% boost in accuracy over the previous state-of-the-art.