policy analysts

Abstract: Ambiguity in prescriptive text such as laws, contracts, rules, policies, or recommendations can be both desirable (e.g., if it enables a law to adapt to changing context, such as new technologies) and undesirable (e.g., if it leads to arbitrary discretion or conflict over the law's interpretation). To help navigate these trade-offs, it would be valuable to have methods for quantifying ambiguity that are predictive of such outcomes, but existing measures capture how text is perceived in isolation rather than how it is interpreted in context. In this paper, we propose quantifying ambiguity as the degree of disagreement among a set of stakeholders ("raters") on how alternative prescriptive texts ("policies") apply in each of a set of relevant scenarios ("cases"). Using two policy domains, we present preliminary analysis suggesting that, even when using simulated raters, this approach (i) correlates with real human disagreement, and (ii) is robust to spurious text features. We then apply the measure to existing deliberation datasets to describe the association between policy ambiguity and support for those policies.

Abstract: Dealing with climate change requires that all countries engage in costly efforts to reduce their emissions. Reaching this objective has so far been elusive because it is in the best interest of each country to let the others do the effort and benefit itself from a better environment. The presence of negative externalities and strategic behavior have made game theory a natural paradigm to design an international environmental agreement (IEA) that codifies what countries should do. Considering that countries are sovereign and no supranational entity can impose an agreement, a stream of literature adopted a noncooperative mode of play to the formation of an environmental coalition. On the other hand, as joint optimization of all countries' payoff leads to the best outcome, cooperative games approach has also been proposed to share the cost of climate change. Both approaches have their pros and cons.

Abstract: We study inverse and consensus analysis for PROMETHEE II ranking problems when the performance table is fixed. Existing approaches in PROMETHEE-based sensitivity and consensus analysis usually focus on deviations of criteria weights while treating preference functions as fixed. Nevertheless both sets of parameters jointly determine the outranking flow scores. We introduce a linear reparametrization of the PROMETHEE II net flow scores based on weighted preference increments over the observed differences of performances. This representation yields a linear expression of the net flows and clarifies how weights and preference functions interact. Building on this result, we derive linear optimization models for three settings: minimizing weight deviations while allowing preference functions to vary; minimizing deviations over the full set of preference parameters; and multiple decision-maker consensus analysis (with objectives based either on total deviation or on the maximal individual deviation to promote fairness). An illustrative example shows that allowing preference functions to vary can dramatically change the inverse-analysis conclusions obtained from weight-only models, and that the proposed group formulations distinguish efficient consensuses from fairer ones.

Abstract: Natural direct and indirect effects are defined through cross-world interventional counterfactuals. We propose an alternative construction based on backtracking counterfactuals. Rather than intervening on the treatment or mediator, we use a backtracking conditional distribution to construct an alternative exogenous state satisfying a desired treatment-mediator constraint. This yields the backtracking direct and indirect effects, and also the backtracking total effect. Likewise, we adapt the population intervention effects.

Abstract: Policy learning from observational data is fundamental to applications ranging from personalized medicine to welfare-program targeting, but standard approaches optimize empirical performance and may fail when the deployment distribution differs from the training distribution. We study \emph{distributionally-robust policy learning}: given observational data, we seek a policy $π\in Π$ that maximizes the worst-case policy value over an $f$-divergence ball of radius $ρ$ around the data-generating distribution. We propose an estimator built on cross-fitted doubly-robust scores for the conditional treatment effect, paired with a DRO solver that handles \texttt{KL}, $χ^2$, and \texttt{CVaR} ambiguity sets. We establish two convergence guarantees. First, the estimated policy attains the standard $\widetilde{O}(n^{-1/2})$ rate on its DRO regret, and inherits the doubly-robust property -- the rate continues to hold whenever either the outcome model or the propensity model is consistently estimated, even at slow nonparametric rates. We then propose a sample-splitting bias-correction algorithm derived from the Lagrangian dual, and show that under a Tsybakov-style margin condition on the treatment-effect, the estimator attains a fast rate of $\widetilde{O}(n^{-(1+α)/(2+α)})$ , interpolating between $\widetilde{O}(1/\sqrt{n})$ and $\widetilde{O}(1/n)$ as the margin parameter $α$ ranges over $[0,\infty)$. To our knowledge, this is the first work to incorporate a margin condition into the analysis of distributionally-robust policy learning, and the first to obtain fast rates in this setting. Empirically, on synthetic and semi-synthetic experiments calibrated to a welfare-to-work program, distributional robustness yields meaningful improvements over empirical welfare maximization when training and test distributions differ.

Abstract: Synthetic control methods estimate counterfactual outcomes by weighting untreated donor units to match a treated unit before treatment. In recent applications, however, the donor pool can be large, highly correlated, and short in pre-treatment history, yielding many near-equivalent solutions with unstable and difficult-to-interpret donor weights. We propose Graph-Regularized Synthetic Control (Graph-SC), a convex estimator that augments the classical pre-treatment matching objective with a graph Laplacian penalty. The graph encodes similarity among donor trajectories, encouraging coherent weights over structurally related donors while preserving the transparency of synthetic controls. We provide theoretical results characterizing the bias-variance tradeoff induced by graph regularization and establish efficient convergence guarantees with an accelerated proximal gradient method. Across a controlled simulation under donor redundancy, the California Proposition 99 benchmark, and observational counterfactual analyses on the Waymo Open Motion Dataset, Graph-SC improves weight stability, reduces sensitivity to redundant donor pools, and maintains competitive pre- and post-treatment accuracy relative to classical and regularized synthetic control baselines. Our results suggest that graph regularization is most valuable not as a universal accuracy booster, but as a principled mechanism for selecting stable and interpretable counterfactuals from near-equivalent synthetic controls with comparable pre-treatment fit.

Abstract: Many questions about large textual corpora concern patterns that unfold over time, such as a political group whose stance on a topic drifts from support to criticism over several years of debates. We present TL;QR (Too Long; Query with logical temporal Reasoning), a declarative query language and open-source engine for finding such temporal discursive patterns. In TL;QR, a single query combines natural-language predicates, whose truth is judged by a Large Language Model (LLM), with regular expressions and the operators of a temporal logic. The LLM answers only local questions about individual text passages; a symbolic engine then aggregates these judgments over time and links every match to the recorded passages and predicate decisions behind it. With this division of labor, the temporal and relational reasoning stays exact and auditable even over long time horizons. In addition, when a query includes a regular-expression pre-filter, only a small fraction of the corpus ever reaches the LLM. On a suite of controlled synthetic benchmarks with temporally and semantically complex patterns, TL;QR is substantially more accurate than LLM-only baselines. In a case study on ten years of European Parliament debates (442,593 multilingual speeches), TL;QR identifies candidate shifts in the political groups' stances on the GDPR privacy regulation.

Abstract: Partial identification (PI) entails estimating bounds on causal effects by encoding different assumptions on data generation as a constrained optimization problem. Such bounds can suffice to inform policy decisions even if the causal effect itself is not identifiable. Often vacuous in practice, practitioners seek to exhaustively encode domain knowledge as additional constraints to make the PI bounds more informative. We introduce known data symmetries -- invariance of the causal effect under certain data transformations -- as a new source of constraints to inform PI. We operationalize this as a shape constraint on the causal function, and via a change of measure against which PI is posed using simple data pre-processing. Both approaches are shown to sharpen bounds under two canonical PI models. This is shown both theoretically for the population case, and via experiments in the finite-sample case. More broadly, our framework establishes data symmetries as a natural, underutilized source of background knowledge for robust causal inference.

Abstract: Large language models (LLMs) increasingly mediate human communication, from drafting emails to summarizing scientific reports, yet whether they faithfully preserve a speaker's position remains largely untested. We model AI-mediated communication as a two-step generation-extraction pipeline: one LLM produces an argument from a specified stance, and a second LLM extracts the stance from that argument. We represent the pipeline as a probabilistic state transition over five Likert-type stance categories and define the stance preservation rate (SPR) as the average probability that the extracted stance matches the initial stance. Across 112 debate propositions, none of the nine LLMs tested exceeded an SPR of 0.7 under the default configuration. Three drift patterns accounted for most of the drift: polarization, deviation from neutrality, and flipping. Among the mitigation strategies tested, including in-context learning, multiple extraction with shuffled options, assertion, and reflection, only adding medium reasoning effort to a reflection prompt for GPT-5.4 substantially improved the SPR, to 0.775, yet polarization remained the largest pattern, with 0.119 of the transition mass. An exploratory comparison with human extraction on a single proposition suggests that drift arises at both the generation and the extraction stage. These results point to a fidelity gap in AI-mediated communication, with implications for journalism, policy deliberation, scientific communication, and other domains where opinion-laden messages pass through language models.

Abstract: Estimating treatment effects from observational data typically relies on the No Unmeasured Confounding Assumption (NUCA), which rarely holds in practice. Proximal causal learning (PCL) addresses unmeasured confounding via proxy variables, yet existing methods require the proxy variables to be pre-specified. Thus, we propose PCL-U, a framework that learns proxy variables directly from observed covariates. PCL-U uses neural encoders to decompose covariates into treatment-inducing, outcome-inducing, and shared proxies, guided by minimax mutual information objectives, and obtains causal estimates through a practical moment-based risk function. Experiments on benchmarks show that PCL-U matches or outperforms existing baselines. Besides, there are two types of synthetic datasets with varying dimensions and confounding strengths that illustrate that our method maintains stable estimation accuracy.

Abstract: An argument can be surprising coming from a particular speaker without being a bad argument. Do AI evaluators keep these judgments apart? Two preregistered descriptive studies and a later Jev supplement collected 2,976 usable evaluations of six fixed texts about US AI policy, Germany's debt brake and Swiss nuclear energy. Each text was presented under several source attributions. The key comparison asks whether the gap between two sources changes when the argument changes. On Sol, for example, a national-security argument received mean ratings of 0.359 under CODEPINK and 0.639 under College Republicans; a civil-rights argument received 0.742 and 0.721. A constant preference for one source cannot explain that pattern. Related interactions appeared across topics and recent model configurations, including those with reasoning enabled, while several comparisons yielded small effects. The later European Jev supplement yielded five interactions below the adopted absolute reference of 0.05; its distinct rubric and interrupted collection limit comparison with the chat systems. Some written evaluations explicitly invoked a mismatch between a source and its attributed position. Taken together, the numerical and verbal evidence supports source-position coherence as a plausible explanation, alongside competing accounts involving credibility, authenticity and interpretation of the task. The paper develops this inference through controlled comparisons, reports conditional post hoc p-values in an appendix, and documents the human decisions and delegated checks behind an AI-conducted study.

Abstract: Public policies addressing urgent social and environmental challenges need to explicitly consider the diverse, often conflicting perspectives of the affected stakeholders. Despite computational decision-support approaches increasingly offering recommendations across diverse human value systems, they still tend to deliver a single consensus-driven outcome. We present KITA AI, a modular system in which multiple large language model agents, each grounded in distinct demographic stakeholder personas and conceptual frameworks, deliberate on policy scenarios. The objective of KITA AI is not merely to inform about a preferred policy proposal, but also to automatically surface who is affected by the scenario and provide decision-makers with the rationales and quantitative indicators behind each position. KITA AI treats non-convergence as a first-class explainable output, enabling policymakers to better understand the trade-offs and human impacts of the policies being discussed.

Abstract: A non-significant coefficient in a dynamic panel model need not imply the absence of a relationship. It may instead reflect heterogeneous effects averaged toward zero, reciprocal dynamics overlooked by a recursive specification, or relationships masked by the omission of correlated covariates. Standard linear estimators cannot distinguish among these possibilities. We develop an inferential workflow for political panel data that resolves this ambiguity by combining flexible autoregressive estimation, forecast-necessity testing, functional characterization, and same-data linear benchmarking. The workflow first identifies relationships required for out-of-sample prediction, then characterizes their functional form across political contexts, and finally, distinguishes differences arising from estimator flexibility from those due to model specification. Applied to the causal sequence model of democratization on the V-Dem panel of 113 countries, the workflow reproduces the model's central finding - the protective belt of civil society, the rule of law, and institutionalized parties - while recovering reciprocal relationships from democracy to its institutional supports that a linear model cannot detect. Most importantly, three weak published direct effects, of which two are null, and one is marginally significant, receive three different diagnoses: one dissolves under the full specification, one reflects heterogeneous effects averaged toward zero, and one was masked by the reduced variable set. The workflow corrects the published record in both directions, removing one relationship and recovering two. More broadly, the workflow provides a framework for evaluating dynamic political theories under a model class capable of representing nonlinear and reciprocal mechanisms while preserving relationship-level interpretation and explicit inferential standards.

Abstract: Artificial intelligence (AI) is reshaping labor markets, yet its effects on wage distribution and the underlying mechanisms remain insufficiently understood. Conventional analytical approaches are limited in their ability to directly examine the dynamic evolution of worker behavior and income distribution under sustained AI shocks and counterfactual policy scenarios. To address this limitation, we present a hybrid agentic framework that aims to challenges of scalability of rule-based models and the limited explainability in LLM-agentic frameworks. Using this framework and sociodemographic data from China, we simulate changes in wage distribution under repeated AI shocks. The results show that both the average-wage ratio between workers in the top and bottom income deciles (T10/B10) and the Gini coefficient increase persistently, suggesting that AI shocks widen the wage gap and exacerbate income inequality. This pattern of a widening wage gap remains robust across alternative large language model decision engines and 30 Monte Carlo simulations. We further conduct counterfactual policy experiments. The results show that education subsidies targeted at low-income workers increase both the number of skill-upgrading attempts and the number of successful upgrades, with particularly pronounced improvements in the upskilling success probability of workers in the bottom income decile. These effects enable the policy to partially mitigate wage inequality. The proposed framework provides an interpretable simulation approach for examining the effects and mechanisms of AI shocks on wage distribution. It also offers policymakers a complementary analytical tool for evaluating policy interventions.

Abstract: We investigate the effectiveness of artificial intelligences (AI)-specifically large language models (LLMs)-relative to human scientists at high-level cognitive tasks in social science such as theory formulation, predictions of novel empirical results, and theory revision in response to new evidence. The research domain was academic discourse regarding gender and race inequality. Our findings, comparing 25 LLMs with 13 senior researchers and 60 doctoral scholars, reveal that the AIs outperformed most humans individually on most of the present tasks, while human theories were more diverse and exhibited greater gains in predictive accuracy from aggregation. AI-generated theories were more extensively elaborated, involving additional theoretical paths and latent variables, and were rated as higher quality than human theories by independent raters blinded to source. However, this theoretical complexity was in part ornamental, in that it was not associated with more accurate predictions about empirical patterns in data; in contrast, human scientists achieved greater predictive efficiency with simpler theories. The AIs were significantly more likely than human scientists to revise their theories to incorporate new evidence; human scientists updated their beliefs in a selective way that is sensitive to prior prediction errors. We speculate that the superior processing capacity of artificial intelligences makes them especially well-suited to tasks requiring grappling with complexity, but that the greater diversity of human ideas is essential to wise crowds and collective creativity.

Abstract: Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptions remains challenging. We introduce ARGUS, a structured language-model pipeline that audits reported evidence against an eleven-dimension assumption-implication-evidence rubric and abstains when relevant evidence cannot be retrieved. We evaluate ARGUS using injected flaws, economics papers, and a small pilot with reconciled labels. On the 11-flaw benchmark, ARGUS detects 73% of planted flaws, compared with 18% for a keyword-based pipeline. Across 26 economics papers, ARGUS abstains on about 40% of paper-dimension assessments for lack of retrievable evidence. In a five-paper pilot with labels reconciled by two annotators, it assigns a higher risk level than the labels on 25 of the 33 assessments it completes. A rule fixed before the labels arrived removes most of this in-sample; weighted agreement stays low. ARGUS provides evidence-linked risk reports that localize potential weaknesses for expert review, without adjudicating causal claims. Code and data: https://github.com/yonghongzhang-io/ARGUS

Abstract: We study a partial-participation variation of the Hotelling-Downs model. Voters each have a cost to vote, and only vote when the comparative gain from their preferred candidate exceeds the cost. Under this model the median voter theorem breaks, and we study the extent of polarization under equilibria in different voters and cost distributions. We find that the main predictor of polarization is the reverse-hazard-rate of the cost distribution, indicating that the driver of polarization under our model is the willingness of voters to respond to changes in positions of candidates. We then extend the model by adding parameters governing alienation and candidate competitiveness, showing that our results are robust even when taking into account other realistic factors.

Abstract: Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention-behaviour gap in behavioural science, we argue that these validations test the wrong thing for most applied cases where decision makers commission synthetic research to anticipate consequential behaviour. To address this problem, we propose a validation framework with two requirements. First, every validity claim must state its level of correspondence with human data: does the sample predict what the represented people do, which of four diagnostics (location, dispersion, response process and structure) does the validation address, and does the validation compare against experimental effects? Second, researchers must report validity claims for subgroups, since these groups are often the most affected by consequential decisions and aggregate accuracy hides their misrepresentation. Our validation framework operationalises three justice dimensions (distributional, procedural, and recognition) as measurable quantities and defines within-persona counterfactual experiments as a validation requirement. We then apply the framework to electric vehicle charging tariffs, before closing with a reporting checklist that researchers can use to make convincing validity claims.

Abstract: KITE queries a typed behavioral kernel once per unique state, then executes populations of any size from the table with event-keyed randomness and common random numbers. An expensive flagship model is reserved for sparse paired anchors that estimate intervention effects. Measured human-model discrepancy is propagated as shared error into every conclusion. Population-experiment cost thus scales with unique states and anchors, while uncertainty is governed by evidence about people rather than Monte Carlo noise. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states reduced effect error by 41% (absolute MAE reduction 0.0125). On 37 held-out SocSci210 experiments, 0.5-1.5% anchor coverage raised captured decision gain from 0.27 to 0.39. The kernel passed content-fidelity criteria in all 15 new countries of a 16-country study. Shared discrepancy yielded retrospective coverage of 93% and 96% at nominal 80% and 90%, versus 29% and 36% from human sampling uncertainty alone. A million agents executed 20 tabulated steps in 0.9 seconds on a laptop. This architecture offers a route to screening candidate interventions before human trials, multi-country content audits, and uncertainty-aware policy comparison at the cost of a few thousand kernel calls with sparse flagship anchors. Property-specific evidence records connect each use to its validation scope, correction provenance, and uncertainty, making these applications auditable.

Abstract: LLM-based social simulations are primarily evaluated for behavioral fit, testing whether agents reproduce the actions or response distributions of the people they are simulating. However, the promise of simulation extends beyond behavioral fit. Simulations can explain human behavior, diagnose barriers, and compare large-scale interventions. These use cases depend on understanding \textit{why} people acted a certain way, not just \textit{what} they did. As a result, behavioral fit is insufficient for these types of claims because behavior underdetermines the reasoning process behind it. For instance, the behavior of staying silent may be due to disinterest or suppressed speech, and not answering a call may be due to distrust of the caller or limited phone access. In this paper, we propose \textit{representational adequacy} as a new evaluation target for LLM-based social simulations. By leveraging LLM reasoning traces, representational adequacy measures whether a simulation's scenario--reasoning--action triples preserve the reasoning process behind the behavior in a way that is faithful to the population and scenarios being simulated. We distinguish representational adequacy from interpretability and alignment metrics, propose ways to integrate it into simulation research, and pose its measurement as an open problem.

Abstract: High annotation reproducibility does not necessarily imply that an LLM-inferred measure captures the construct it is intended to measure. We test this distinction using a dataset from the European Commission's AI Act consultation, linking structured survey responses to free-text consultation submissions from the same stakeholders. LLM annotations of consultation submissions are highly reproducible (intraclass correlations > 0.99), yet show limited convergence with survey-reported measures of the nominal construct they were intended to approximate. Divergence between survey-and LLM-inferred text-based measures varies systematically across stakeholder groups: business associations express greater concern about AI risks in text-based consultations than in survey responses ({g} = +1.0), whereas public authorities and several nonbusiness groups show smaller or negative divergences. Divergences between scores suggest positive spatial autocorrelation across European countries (Moran's I = 0.347, p = 0.036), indicating that stakeholders from neighboring countries tend toward more similar text-based stances towards AI safety concerns. Despite divergence, survey-reported concerns remain strongly associated with support for explainability across all divergence levels. These results demonstrate that LLM annotation reproducibility can coexist with poor construct correspondence and motivate validation procedures that distinguish reproducibility, construct validity, and communication context variation when LLMs are used as measurement instruments.

Abstract: As technological and social innovations create novel regulatory challenges, legal systems grow in complexity - increasing the need for interfaces that enable effective interactions with legal document collections. Through interviews with legal scholars (n=15), we find that supporting legal work requires going beyond retrieval-centered legal-information-system paradigms. Hence, we propose Lexplorer, a flexible interface for exploring, navigating, and analyzing legal documents, based on a taxonomy capturing user intents. Distinguishing text and data views for one, few, and many documents, Lexplorer enables context-sensitive interactions with evolving collections of interconnected legal texts, facilitating Adaptive Meaning Construction in law. We evaluate Lexplorer with legal scholars (n=20) in the context of European Union law, validating our elicited requirements, intent taxonomy, and prototype design. Resulting from a close collaboration between visual-analytics researchers and legal scholars, our work also provides nuanced insights into the process required to design interactive systems for expert domains driven by implicit methodological knowledge.

Abstract: Foundational frameworks in visualization have operationalized literacy as an individual competency, measured through chart-comprehension tasks. This focus raises a question: why has measurement become the dominant frame for understanding literacy? Rather than asking whether literacy should be measured, we ask how measurement became the field's way of understanding it. We trace visualization literacy back through the history of textual literacy and argue that in adopting the term, the field imported three values rooted in early government statistics: quantification, individualization, and binary classification. To mark the shift this history makes possible, we distinguish two waves: a first centered on assessment and individual proficiency, and a second that treats literacy as a situated practice, attentive to how people use visualizations in context and to the purposes they serve. Examining the construct this way suggests that refining assessment instruments does not, by itself, settle what literacy is, and points to directions for second-wave research: formative studies of literacy in context, culturally grounded instruments, and critical reading. This paper shows that visualization literacy inherited its measurement frame rather than discovering it, offers a two-wave vocabulary distinguishing assessment-based literacy from situated practice, and connects the field to a critical-literacy tradition with concrete alternatives to measurement. These contributions allow us to treat measurement and meaning as two parts of a single question, shifting attention from who counts as literate to what literacy is meant to do.

Abstract: Understanding how humans respond to incentives, both at the individual and collective levels, is crucial to the design of effective policies. Within the continuous-time stochastic framework for large interacting populations, mean field games (MFGs) model populations of non-cooperative agents, whereas mean field control (MFC) describes the fully cooperative benchmark, interpreted in our setting as fully altruistic behavior. Mixed-individual MFGs interpolate between these two extremes through a parameter governing the degree of altruism. A central challenge for regulators and policymakers, however, is that intrinsic altruism levels and other private structural parameters, such as individual labor costs, are typically unobservable. To address this challenge, we develop an inverse learning framework for mixed-individual MFGs. Our approach enables the recovery of (latent) altruism and labor cost levels from noisy observations, with experiments demonstrating the feasibility and accuracy of our method. These findings underscore the promise of inverse MFG methodologies for uncovering latent preference structures in large populations, with important implications for incentive design, empirical behavioral modeling, and data-driven policy analysis.

Abstract: Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with documents from the makers of drugs, chemicals, food, firearms, and fossil fuels. Yet these archives have been effectively inaccessible to general-purpose large language models (LLMs) because they have never been compiled into an LLM-readable corpus. Chatbots may be familiar with some of the materials contained in such archives but, with no direct access to the documents, they are vulnerable to hallucination and other defects. Here we introduce INDRA, a research platform designed to remedy such failures by embedding the conventions of archival historiography into a system-level protocol governing every output. The platform federates UCSF's Industry Documents Library, Columbia and CUNY's ToxicDocs, Stanford's SRITA, and other heretofore siloed collections, and provides three interlinked safeguards: (1) a closed evidentiary sandbox confines the model to a user-selected corpus, blocking retrieval from external sources that could introduce bias; (2) real-time provenance tagging marks the boundary between archival evidence and parametric inference; and (3) a system-level protocol enforced by deterministic scripts guides the structure of every output. Together these safeguards prevent the model from conflating "the documents say X" with "I think X" or "I learned X from prior training." The result is an LLM-powered research partner enabling massive multi-archival investigations, a tool whose outputs are designed to be checked rather than trusted, and whose architecture makes the conditions of knowledge production visible and auditable. Three case studies demonstrate the method's analytical value and limitations, including what we call the Heraclitus effect, the steppingstone dilemma, and the gullibility (or mafia) problem.

Abstract: Large Language models (LLMs), having been trained on vast amounts of human-generated data, may encode the attitudes and behaviors of these humans. As such, LLMs show promise in mimicking human-like patterns that facilitate their use in simulating people in a wide variety of contexts. One such context is using LLMs as 'silicon samples', i.e., proxies of people in answering survey questions to establish public opinion, design policies, or use as (social) scientific data. However, several critical questions of social biases, generalization, and technical limitations remain, further complicated by a vast design space open to simulation designers. Multiverse analyses might help us make sense of the impact of different design choices, however, we lack a systematic understanding of the design space of LLM-generated surveys as well as how these decisions interplay with inherent LLM limitations. Therefore, how do we systematically identify, trace, and document limitations in LLM-generated survey responses? Building on traditions in the quantitative social sciences, specifically survey methodology and measurement theory, we investigate threats to the validity of LLM-generated survey responses. To do so, we design a framework that enumerates conceptual errors and systematic biases that can occur at different stages of the survey simulation lifecycle. Our framework, called the Total Simulated Survey Error (TS2E) Framework, provides a unified and end-to-end perspective on LLM-generated survey data. The framework, illustrated through a theoretical and empirical case study, enables survey simulation designers to systematically identify and reflect on errors in LLM-generated surveys.

Abstract: LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We study when and how a defendant's courtroom statement affects LLM-simulated jurors, focusing on persuasion, ideological bias, and background-based affinity. To support the analysis, we introduce JuryBench, a benchmark containing controversial criminal cases in U.S. criminal law. In each case, a defendant can claim various plausible justifications to support acquittal or reduced liability. We fix the base case and design defendants of different backgrounds, who give courtroom statements with varying emotional appeal or rebuttal. Jurors with diverse ideological profiles across the spectrum are simulated. We examine 20 frontier LLMs, resulting in a total of 432K decisions and rationales, and quantify changes in verdict severity. Our findings show that LLM-jury simulation echoes many human-jury findings. First, emotional persuasion can be detrimental, since jurors may perceive it as evidence of guilt or inconsistency. Next, we show that background fit between jurors and defendants is a stronger and significant factor than other isolated factors, and that jurors are in general harsher toward opposite-background defendants and lenient toward same-background ones. Finally, we find that juror ideology also strongly shapes severity judgments. These findings highlight both the promise and risks of using LLMs to model jury reasoning and call for careful evaluation. The data and code are available at https://github.com/choyingw/JuryBench

Abstract: Average treatment effect (ATE) estimation in observational studies is a fundamental statistical tool used frequently in social science, medicine, and other fields. These fields often work with sensitive data where privacy protections are important, so a differentially private mechanism for ATE estimation is highly desirable. Here we present two propensity score-based algorithms for ATE estimation on observational data, one improving the inverse probability weighting (IPW) method used in prior work, and the other using blocking on the propensity score (BPS). Both show lower error and less bias than prior work, with the BPS-based algorithm frequently reducing error by 75% or more compared to prior work.