arXiv AI September 3, 2026 By Wenxin Jiang, Xuyang Wang, Yuxiao Wu

AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application

The paper introduces AICOME, a framework that uses AI-derived respondent-level measures to recover both individual and group-level effects in contextual models. By applying AICOME to the 2022 China Family Panel Studies, the authors validate that AI measures can replicate key survey variables such as computer use, foreign-language use, weekly hours, and management responsibilities, especially when rich respondent and job data are available. The study also identifies boundary conditions, noting reduced performance when only occupation and basic demographics are used or when multiple related constructs are simultaneously unobserved.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Aug 20

Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements

The paper introduces Debiased Inference with Multiple Imperfect Measurements (DMM), a framework that uses several error‑prone AI measurements to perform valid downstream statistical inference without requiring costly gold‑standard labels. By assuming conditional independence of the measurements given the true label and unit‑level features, DMM leverages CP decomposition and semiparametric theory to prove consistency and asymptotic normality of its estimator. Simulations demonstrate that DMM yields valid inference and can improve efficiency when additional imperfect measurements are available, and the authors provide diagnostics for the key independence assumption.

By Naoki Egami, Sooahn Shin

llms rag safety

arXiv AI

Jun 3

Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

arXiv:2510. 21011v3 Announce Type: replace-cross Abstract: As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical.

By Ilona van der Linden, Sahana Kumar, Arnav Dixit, Aadi Sudan, Smruthi Danda, David C. Anastasiu, Kai Lukoff

llms safety

arXiv AI

Aug 18

A validity-guided workflow for robust large language model research in psychology

arXiv:2507. 04491v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly being integrated into psychological and behavioral research as research tools, evaluation targets, human simulators, and cognitive models.

By Zhicheng Lin

llms

arXiv AI

Aug 18

Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents

arXiv:2608. 14606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the individual level.

By Mantas Lukauskas, Viktorija \v{S}arkauskait\.e

llms benchmarks

arXiv AI

Jun 30

LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

arXiv:2411. 10109v3 Announce Type: replace Abstract: Machine learning can predict human behavior well when substantial structured data are available for well-defined outcomes.

By Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst, Niles Egan, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Percy Liang, Robb Willer, Michael S. Bernstein

llms agents benchmarks

arXiv Machine Learning

Jun 24

BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks

arXiv:2606. 24162v1 Announce Type: cross Abstract: Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics.

By Jin Huang, Yutong Xie, Wanli Song, Xingjian Zhang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei

fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements

Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

A validity-guided workflow for robust large language model research in psychology

Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents

LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals

BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks