# ALBA: Adaptive Language-based Assessments for Mental Health

arXiv: https://arxiv.org/abs/2311.06467 · HTML: https://mlsanity.com/paper/2311.06467/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 45 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 1 of 1)

- [Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality](https://mlsanity.com/paper/2105.03484/) (2021)

## Built on by (most cited first, 6 of 6)

- [JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory](https://mlsanity.com/paper/2509.22888/) (2025)
- [Explaining GPTs' Schema of Depression: A Machine Behavior Analysis](https://mlsanity.com/paper/2411.13800/) (2024)
- [Responsible Evaluation of AI for Mental Health](https://mlsanity.com/paper/2602.00065/) (2026)
- [MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory](https://mlsanity.com/paper/2508.07279/) (2025)
- [ISCA: A Framework for Interview-Style Conversational Agents](https://mlsanity.com/paper/2508.14344/) (2025)
- [A Systematic Evaluation of Large Language Models for PTSD Severity Estimation: The Role of Contextual Knowledge and Modeling Strategies](https://mlsanity.com/paper/2602.06015/) (2026)

## Abstract (arXiv)

Mental health issues differ widely among individuals, with varied signs and symptoms. Recently, language-based assessments have shown promise in capturing this diversity, but they require a substantial sample of words per person for accuracy. This work introduces the task of Adaptive Language-Based Assessment ALBA, which involves adaptively ordering questions while also scoring an individual's latent psychological trait using limited language responses to previous questions. To this end, we develop adaptive testing methods under two psychometric measurement theories: Classical Test Theory and Item Response Theory. We empirically evaluate ordering and scoring strategies, organizing into two new methods: a semi-supervised item response theory-based method ALIRT and a supervised Actor-Critic model. While we found both methods to improve over non-adaptive baselines, We found ALIRT to be the most accurate and scalable, achieving the highest accuracy with fewer questions (e.g., Pearson r ~ 0.93 after only 3 questions as compared to typically needing at least 7 questions). In general, adaptive language-based assessments of depression and anxiety were able to utilize a smaller sample of language without compromising validity or large computational costs.