Skip to content
AI News HubLIVE
Original source2 min read

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

Summary

A study with 3,011 UK adults and seven LLMs finds that AI-human correlation in perceived sympathy in news headlines ranges from 0.789 (GPT-5.2) to 0.4 (Mistral Large 2512). Leading models broadly align across demographic subgroups, but significant differences remain, highlighting the need for differential alignment.

SourcearXiv Computational LinguisticsAuthor: Haran Shani-Narkiss, Michael Fire, Oren Tsur
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
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 22 Jul 2026]

Title:Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

View a PDF of the paper titled Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups, by Haran Shani-Narkiss and 2 other authors

View PDF HTML (experimental)

Abstract:Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview. This raises concerns beyond bias in AI: do LLMs grasp the emotional nuances conveyed via textual framing? In this work, we empirically evaluate how well an array of LLMs aligns with human emotional perception. Considering news headlines covering political and geopolitical conflicts, both human participants (n = 3011, a representative sample of the U.K. adult population, via a YouGov survey) and seven LLMs answered whether headlines evoked sympathy for a specified side in a conflict. We find that the correlation between AI and human evaluations varies across models, ranging from very high (0.789, GPT-5.2) to medium (0.4 ,Mistral Large 2512). Crucially, the leading models are broadly aligned with human judgments across all demographic subgroups, including age, gender, level of education, prior geopolitical knowledge, and participants' predispositions regarding the conflict, although there are statistically significant differences between groups. This research, with its robust design and large, demographically diverse dataset, offers the most comprehensive evaluation of LLMs' comprehension of news framing to date. Findings highlight an important, often-ignored aspect of differential alignment: even when aggregate performance is high, AI alignment is not universal -- it may correspond differently with demographic features and cultural norms. Considering or ignoring the need for differential alignment may therefore have significant implications for the development of ethical and useful AI systems.

Subjects:

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

Cite as: arXiv:2607.27232 [cs.CL]

(or arXiv:2607.27232v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.27232

arXiv-issued DOI via DataCite

Submission history

From: Oren Tsur [view email] [v1] Wed, 22 Jul 2026 16:23:26 UTC (3,908 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups, by Haran Shani-Narkiss and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

cs cs.AI cs.CY cs.LG

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?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Human participants (n=3011, UK representative sample) and seven LLMs judged whether news headlines evoked sympathy for a specified side in a conflict.
  • Correlation between AI and human evaluations varies widely: GPT-5.2 reaches 0.789, while Mistral Large 2512 is at 0.4.
  • Top models align with human judgments across age, gender, education, geopolitical knowledge, and conflict predispositions, but statistically significant group differences exist.
  • Aggregate high performance does not guarantee universal alignment; differential alignment matters for ethical and useful AI systems.

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