RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons

Discovering stable neuron behavior across entire domains remains a challenge in mechanistic interpretability. Existing methods often rely on instance-level point estimates or computationally expensive procedures, which either obscure population-level variability or limit scalable domain-wide analysis. We present RACE (Residual Alignment for Consistency Estimation), a forward-pass statistical framework that evaluates the domain-wide functional consistency of Transformer neurons. Perturbation experiments demonstrate that RACE achieves superior domain specificity compared to gradient-based point estimates. Meanwhile, token-distribution-level results verify the association between the selected neurons and the target domain. Furthermore, its computational overhead is two orders of magnitude lower than that of gradient-based methods.

Statistically Supported LLM Ingredient and Recipe Data Collection in Computational Nutrition

Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning. LLMs could help fill these gaps, but single-pass outputs are unreliable and can introduce silent errors into downstream computation. We present a quality-controlled LLM pipeline for ingredient data acquisition that combines robust statistical estimation, domain-specific invariant checks, and a web-fetch fallback. An illustrative Heap's Law fit to 233 recipes suggests that unique-ingredient growth is sub-linear and front-loaded: the projected ratio of unique ingredients to recipes falls from 1.74 at 100 recipes to 0.19 at 5,000. For each ingredient attribute, repeated LLM queries are treated as samples from a model-induced answer distribution, and we apply robust point estimators and normalised confidence scores across numerical, Boolean, multiple-choice, open categorical, and optional integer types. An invariant guard layer enforces nutritional and logical self-consistency within each ingredient record. Minor numeric inconsistencies are reconciled via a linear program that minimises worst-case percentage deviation while preserving semantic zeros, and major violations are escalated to web-evidence-grounded repair, then human review only if that fails. On a curated 30-ingredient reference set, the pipeline achieves 98.4% exact match on nutrient flags and cuts median absolute percentage error on nutrient ratios from 31.9% for the median-aggregated baseline to 10.1%, a reduction of 21.8 percentage points, at an API cost of about $1 per ingredient. This frames LLM-assisted database construction as a controlled data-engineering workflow that makes uncertainty operational rather than discarding it.

Scalable Model-Assisted Multi-Target Estimation in Large Image Collections

Computer vision models are increasingly used as measurement tools to estimate population-level quantities from large image collections, but prediction errors introduce bias and the resulting estimates lack statistical guarantees required in scientific applications. Prior work uses a Monte Carlo framework to combine model predictions with ground-truth annotations by sampling some images for humans to label and is able to provide unbiased estimates with controllable accuracy, but primarily addresses single-scalar estimation. We study the more general problem of multi-target estimation, where many quantities (e.g., class counts or proportions) must be estimated simultaneously, and adapt sampling and estimation strategies from survey sampling to this setting. Evaluations on five detection and segmentation datasets with 7-80 classes show that importance sampling excels with moderate annotation budgets or fewer targets, whereas uniform sampling with control variates is superior when estimating many targets or operating with minimal labels. Additionally, a subset-based ratio estimator remains highly competitive across all regimes. Ultimately, our framework effectively combines biased model predictions and limited human labels into rigorous scientific measurements.

Stabilized Higher-Order Influence Functions: Statistical Theory of a Class of Bilinear Forms

Higher-order influence functions, introduced in a series of articles (Robins et al., 2008, 2009a; van der Vaart, 2014; Robins et al., 2016, 2023; Liu et al., 2017), are a unified framework for constructing rate-optimal point estimates of a class of statistical functionals, under various complexity-reducing assumptions on the posited statistical model that generates the observed data. Although higher-order (influence functions) estimators are theoretically appealing, they have very limited practical uptake compared to their first-order counterparts. The original higher-order estimators proposed in Robins et al. (2008) and Robins et al. (2017) involve nonparametric density estimation of multi-dimensional covariates, a highly nontrivial statistical and computational problem on its own. The density estimator is, in turn, used in the evaluation of the inverse population Gram matrix $Ω$ of a set of $k$-dimensional basis transformations of covariates. There, $k$ is allowed to be as large as $o (n^2)$. To partially address this potential shortcoming, Liu et al. (2017) restrict $k$ to $o (n)$ and instead estimate $Ω$ directly using the inverse sample Gram matrix estimator, but computed from an independent sample often obtained by sample-splitting. Liu et al. (2017) refer to this alternative estimator as the empirical higher-order estimator. Although the empirical higher-order estimator bypasses density estimation, it suffers from numerical instability due to potentially inverting a large-dimensional sample Gram matrix. In this article, we propose a new stabilized higher-order estimator without sample splitting, which exhibits more stable finite-sample performance compared to the empirical higher-order estimator, and more importantly, we prove that this new class of higher-order estimators enjoys similar statistical guarantees.

Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data

Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias. Here we show that pretrained large language models induce risk-equivalent estimators of conditional expectations under squared loss, establishing restricted functional risk equivalence: under squared loss, the LLM induces an estimator whose risk matches the Bayes optimal risk for squared-loss prediction of conditional expectations for any inference that depends on the data only through the conditional mean. We formalize the LLM as a misspecified functional estimator $T(\hat{P}_n)$ trained on i.i.d.\ data, decompose the estimation error into representation bias $ε_{\mathrm{rep}}$ and optimization error, and prove that under mild regularity conditions the LLM's expected error converges to the irreducible population variance plus the squared representation bias, with the representation bias bounded by the Pinsker inequality. The identifiability error $δ$ propagates into the effective bias, inflating the asymptotic risk floor. We establish restricted functional risk equivalence via a bidirectional Le Cam deficiency analysis: the forward deficiency vanishes asymptotically while the reverse deficiency is exactly zero. We provide finite-sample concentration bounds and a calibration protocol with explicit decision rules. The result is a precise, provable statement: a well-calibrated LLM achieves the Bayes-optimal risk for conditional-mean-dependent inference, bounded by explicit scope conditions. In practical applications, this means that under satisfied conditions and well-calibrated models, large language models can be used in many prediction and decision-making tasks that originally relied on human experiments, approximating near-optimal statistical inference at lower cost.

When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews

AI-assisted interviews promise to reduce respondent burden in surveys by allowing respondents to describe experiences naturally while an AI system noisily maps those accounts into structured survey variables. That mapping is a measurement process that is fallible, versioned, adaptive, and potentially behaves differently across subgroups. This paper proposes Adaptive Matrix Validation (AMV), a design in which each respondent completes an AI-assisted interview, which is then mapped into tabular data by the AI. Respondents are also asked a small, randomized set of structured questions, which are used for statistical adjustment. The estimator first calibrates the mapped values using validation answers from other respondents, then corrects the remaining error with the validation answers observed for the target respondent. The paper develops estimators for item means, subgroup estimates, and regression coefficients when outcomes, predictors, or both are mapped from interviews. It also gives planning formulas the number of validation questions required and the sample size. A design-calibration simulation, an American Time Use Survey emulation, and a CHAMPS verbal-autopsy narrative study show when sparse validation can improve precision and when it cannot