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

arXiv: https://arxiv.org/abs/2606.24244 · HTML: https://mlsanity.com/paper/2606.24244/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 70 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models](https://mlsanity.com/paper/2306.04746/) (2023)
- [An Integrated System for Mobile Image-Based Dietary Assessment](https://mlsanity.com/paper/2110.01754/) (2021)
- [Another look at statistical inference with machine learning-imputed data](https://mlsanity.com/paper/2411.19908/) (2024)
- [OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking](https://mlsanity.com/paper/2305.09688/) (2023)
- [A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment](https://mlsanity.com/paper/2106.11776/) (2021)
- [From Narratives to Numbers: Valid Inference Using Language Model Predictions from Verbal Autopsy Narratives](https://mlsanity.com/paper/2404.02438/) (2024)
- [A Unified Framework for Inference with General Missingness Patterns and Machine Learning Imputation](https://mlsanity.com/paper/2508.15162/) (2025)
- [Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition](https://mlsanity.com/paper/2409.16954/) (2024)
- [Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla](https://mlsanity.com/paper/2507.01931/) (2025)
- [Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages](https://mlsanity.com/paper/2503.23542/) (2025)
- [Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data](https://mlsanity.com/paper/2512.05456/) (2025)
- [Spatially Robust Inference with Predicted and Missing at Random Labels](https://mlsanity.com/paper/2603.11368/) (2026)
- [AI-Assisted Conversational Interviewing: Effects on Data Quality and Respondent Experience](https://mlsanity.com/paper/2504.13908/) (2025)
- [A Moment-Based Generalization to Post-Prediction Inference](https://mlsanity.com/paper/2507.09119/) (2025)

## Abstract (arXiv)

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