AI News HubLIVE
Original source2 min read

Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias

arXiv:2608.20347v1 Announce Type: new Abstract: Language models (LMs) often pass behavioral bias evaluations, but it remains unclear whether they no longer represent the underlying associations that give rise to biases, or have merely learned not to express them. In this study, we show that representational biases are often detectable, even when behavioral biases are not visible. We introduce a causal framework that decomposes occupational bias into two measurement points: a model's internal representation of a user's competence, and its observable outputs. We derive steering vectors for representations of user expertise, and verify that they causally mediate model behavior in both a question-answering task and a hiring task. Applying this framework to several open-weight models, we find that demographic attributes, such as gender, race, and socioeconomic status, influence a model's representation of user expertise, even in cases where behavioral metrics detect no disparity between demographics. We show that these model representations can influence downstream behavior under intervention, suggesting failure modes that behavioral metrics alone may not detect.

SourcearXiv Computational LinguisticsAuthor: Keren Fuentes, Aaron Mueller

-->

[Submitted on 15 Jun 2026]

Title:Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias

View a PDF of the paper titled Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias, by Keren Fuentes and Aaron Mueller

View PDF HTML (experimental)

Abstract:Language models (LMs) often pass behavioral bias evaluations, but it remains unclear whether they no longer represent the underlying associations that give rise to biases, or have merely learned not to express them. In this study, we show that representational biases are often detectable, even when behavioral biases are not visible. We introduce a causal framework that decomposes occupational bias into two measurement points: a model's internal representation of a user's competence, and its observable outputs. We derive steering vectors for representations of user expertise, and verify that they causally mediate model behavior in both a question-answering task and a hiring task. Applying this framework to several open-weight models, we find that demographic attributes, such as gender, race, and socioeconomic status, influence a model's representation of user expertise, even in cases where behavioral metrics detect no disparity between demographics. We show that these model representations can influence downstream behavior under intervention, suggesting failure modes that behavioral metrics alone may not detect.

Subjects:

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

Cite as: arXiv:2608.20347 [cs.CL]

(or arXiv:2608.20347v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2608.20347

arXiv-issued DOI via DataCite

Submission history

From: Keren De Jesus Fuentes [view email] [v1] Mon, 15 Jun 2026 15:03:52 UTC (1,101 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias, by Keren Fuentes and Aaron Mueller

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-08

Change to browse by:

cs cs.AI cs.CY

References & Citations

NASA ADS

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?)