Skip to content
AI News HubLIVE
Original source2 min read

Tracing Psychometric Inference in Large Language Models

Summary

This study uses a cross-persona paradigm across 14 model variants from Llama 3 and Qwen 2.5 to test whether LLMs internally represent psychological constructs. Larger instruct models reproduce and amplify human cross-scale correlations; internal geometry aligns with the human matrix and correlates with behavioral amplification, but a probe-behavior gap termed readout attenuation remains, and the measured directions are not shown to mediate outputs.

SourcearXiv AIAuthor: Chih-Hao Hsu, Feng-Chun B. Chou, Pin-Hao A. Chen
Tracing Psychometric Inference in Large Language Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 6 Nov 2026]

Title:Tracing Psychometric Inference in Large Language Models

View a PDF of the paper titled Tracing Psychometric Inference in Large Language Models, by Chih-Hao Hsu and 2 other authors

View PDF HTML (experimental)

Abstract:Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across 14 model variants from two families (Llama 3 and Qwen 2.5, 0.5B-14B, base and instruct). Given responses on one psychological scale from real individuals (N = 272 Taiwanese university students), models predict responses on six other scales. At the behavioral level, larger variants reproduce and amplify human cross-scale correlations; amplification persists after correcting the seven-scale human correlations for measurement attenuation. We then examine whether this structure is reflected internally. Contrastive direction analysis finds geometry aligned with the human matrix in larger instruct variants, but little alignment in base variants under this assay. Across models, geometry strength is associated with behavioral amplification (r = 0.68, p = 0.008; partial r = 0.69 controlling for log size). To relate internal structure to output behavior, a matched activation-probing paradigm shows that probe slopes vary less than behavioral slopes (1.38-1.77 vs 0.52-1.53). A synthetic control shows that ridge probing can inflate these slopes; after subtracting a baseline based on a reliability proxy from another analysis, adjusted slopes remain associated with behavior (r = 0.88). We term the measured probe-behavior gap readout attenuation. These results establish decodability and geometric alignment under the tested assays, without showing that the measured directions mediate the cross-persona answers.

Comments: Accepted at NeurIPS 2026

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2611.12937 [cs.AI]

(or arXiv:2611.12937v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.12937

arXiv-issued DOI via DataCite

Submission history

From: Chih-Hao Hsu [view email] [v1] Fri, 6 Nov 2026 14:29:19 UTC (7,707 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Tracing Psychometric Inference in Large Language Models, by Chih-Hao Hsu and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs cs.CL

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Larger instruct variants reproduce and amplify human cross-scale correlations
  • Internal geometry aligns with the human correlation matrix and correlates with behavioral amplification (r=0.68)
  • A probe-behavior gap is termed readout attenuation

Highlights and analysis are generated automatically and may contain errors. Check the original source.

Tracing Psychometric Inference in Large Language Models | AI News Hub