AI News HubLIVE
原文

Cultural Value Alignment Via Latent Activation Steering in Large Language Models

This paper proposes a generalizable framework for cultural evaluation and intervention in LLMs, using scenario-based behavioral probing and activation steering to shift internal alignments without retraining. Experiments reveal latent entanglement between cultural dimensions, limiting precise value alignment.

Article intelligence

EngineersAdvanced

Key points

  • Proposes scenario-based probing with 300 situational dilemmas to map latent cultural values
  • Introduces activation steering to adjust internal representations during forward pass
  • Finds consistent latent entanglement where steering one dimension shifts others

Why it matters

This matters because proposes scenario-based probing with 300 situational dilemmas to map latent cultural values.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26365] Cultural Value Alignment Via Latent Activation Steering in Large Language Models

[Submitted on 25 May 2026]

Title:Cultural Value Alignment Via Latent Activation Steering in Large Language Models

View a PDF of the paper titled Cultural Value Alignment Via Latent Activation Steering in Large Language Models, by Trung Duc Anh Dang and 1 other authors

View PDF HTML (experimental)

Abstract:Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional direct prompting of LLMs on WVS often fails to access the model's latent cultural depth, leading to safety-aligned refusals or neutral responses. Here, we propose a generalizable framework for cultural evaluation and intervention that transitions from abstract queries to scenario-based behavioral probing. By extracting implicit token probabilities across 300 situational dilemmas, we bypass surface-level alignment to map the latent coordinates of LLMs cultural value. We further introduce activation steering to shift these internal alignments during the forward pass without retraining. Across multiple LLMs, we find substantial variation in adaptability and uncover a consistent phenomenon of latent entanglement, where interventions along one cultural dimension induce shifts along another. These results suggest that cultural values are encoded as coupled structures, limiting precise alignment. This work establishes a computationally efficient framework for cultural steering, highlighting the structural complexities when navigating global value with LLMs.

Comments: ACL 2026 Student Research Workshop (Non-Archival Track)

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2605.26365 [cs.CL]

(or arXiv:2605.26365v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.26365

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Trung Duc Anh Dang [view email] [v1] Mon, 25 May 2026 22:20:52 UTC (7,210 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Cultural Value Alignment Via Latent Activation Steering in Large Language Models, by Trung Duc Anh Dang and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs

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?)