Evidence map›Paper›PMID 41783807›Full record

ArticleNPJ artificial intelligence2026

PsychAdapter: adapting LLMs to reflect traits, personality, and mental health.

Huy Vu, Huy Anh Nguyen, Adithya V Ganesan, Swanie Juhng, Oscar N E Kjell, Joao Sedoc, Margaret L Kern, Ryan L Boyd, Lyle Ungar, H Andrew Schwartz and 1 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ artificial intelligence, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.

0numbers the graph read from it
0cells of the map it votes in
1citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

1 citing paper in PubMed.

  1. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

Huy VuComputer Science Department, Stony Brook University, Stony Brook, NY USA.
Huy Anh NguyenComputer Science Department, Stony Brook University, Stony Brook, NY USA.
Adithya V GanesanComputer Science Department, Stony Brook University, Stony Brook, NY USA.
Swanie JuhngComputer Science Department, Stony Brook University, Stony Brook, NY USA.
Oscar N E KjellComputer Science Department, Stony Brook University, Stony Brook, NY USA.
Joao SedocStern School of Business, New York University, New York, NY USA.
Margaret L KernCentre for Wellbeing Science, University of Melbourne, Melbourne, VIC Australia.
Ryan L BoydDepartment of Psychology, University of Texas at Dallas, Richardson, TX USA.
Lyle UngarComputer and Information Science, University of Pennsylvania, Philadelphia, PA USA.
H Andrew Schwartz *Computer Science Department, Stony Brook University, Stony Brook, NY USA.
Johannes C Eichstaedt *Psychology Department & Institute for Human-Centered AI, Stanford University, Stanford, CA USA.

Funding

Large-scale Data Scientific Assessment of Unhealthy Alcohol Consumption Among Front-Line Restaurant WorkersR01AA028032 · NIAAA · STATE UNIVERSITY NEW YORK STONY BROOK · PI SCHWARTZ, HANSEN ANDREW · 2020 to 2023
$2.5M
SCH: Advancing Language-based Analyses of Social Media to Reliably Monitor Variation in PopulationR01MH125702 · NIMH · STATE UNIVERSITY NEW YORK STONY BROOK · PI EICHSTAEDT, JOHANNES C., SCHWARTZ, HANSEN ANDREW · 2021 to 2024
$1.2M
NIAAA NIH HHS R01 AA028032NIMH NIH HHS R01 MH125702
6 · The paper itself

Abstract

AI language generators are now ubiquitous but typically produce generic text that fails to reflect individual differences. Here, we introduce PsychAdapter, a lightweight LLM architectural modification that uses empirically derived links between language and personality, demographic, and mental health traits to generate trait-reflective text, regardless of prompt. PsychAdapter was applied to GPT-2, Gemma-2B, and LLaMA-3, and expert raters confirmed that the generated text matched the specified traits: it produced Big Five personality traits with 87.3% and depression and life satisfaction with 96.7% accuracy. PsychAdapter is a novel method for embedding psychological behavioral patterns into language models by conditioning every transformer layer, without relying on prompting. Beyond personality-conditioned generation, this approach has potential uses for simulated patients reflecting psychopathology and translation tailored to reading or educational level. It also enables generation of characteristic sentences for studying the language of traits, expanding the language processing toolkit for psychology.

Indexed as

Mathematics and computingPsychology

Identifiers

PMID41783807
PMCPMC12953147

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.