AI News HubLIVE
Original source2 min read

Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

State-of-the-art toxicity detectors for text-to-image generation are found to fail marginalized communities: about 35% of images labeled safe are considered harmful by disability communities. This paper advocates for community-specific toxicity detection (CTD) and demonstrates its feasibility with safety guidelines for dwarfism and blind/low vision communities. Experiments reveal that general-purpose detectors achieve F1 scores lower than random (0.32, 0.37) in zero-shot settings, while prompt-based methods improve up to 0.78 (GPT-4o). However, CTD performance still lags far behind general-purpose detection (F1≈0.9), highlighting the need for sustained research.

SourcearXiv Computer VisionAuthor: Xinnuo Xu, Anja Thieme, Daniela Massiceti, Ioana Tanase, Rita Marques, Melanie Fernandez Pradier, Martin Grayson, Camilla Longden, Cecily Morrison

-->

[Submitted on 27 Jul 2026]

Title:Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

View a PDF of the paper titled Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed, by Xinnuo Xu and 8 other authors

View PDF HTML (experimental)

Abstract:State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users. Our empirical evidence shows that these detectors fail to shield marginalized communities: approximately 35% of generated images labeled safe are considered harmful by disability communities. In this position paper, we argue for community-specific toxicity detection (CTD). To demonstrate its feasibility, we collaborate with disability experts to develop safety guidelines for two communities: dwarfism and blind/low vision. Using a dataset of 2,400 annotated T2I-generated images we demonstrate that both large vision-language models and existing general-purpose toxicity detectors catastrophically fail to recognize harmful content under these guidelines in zero-shot settings with F1 score lower than random guessing (F1 0.32 and 0.37). Promisingly, prompt-based adaptation methods (ICL, VQA) substantially improve harm detection performance (GPT-4o: F1 0.50 and 0.78), while parameter-efficient fine-tuning improves smaller models (0.5b-7b with best F1 0.48 and 0.59) with less than 100 demonstrations, but remains sensitive to evolving guidelines. Despite these gains, CTD performance remains far below F1 $\approx 0.9$ achieved for general-purpose toxicity detection, highlighting the challenge and the need for sustained research effort.

Comments: 18 pages, under review

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.24898 [cs.CV]

(or arXiv:2607.24898v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2607.24898

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xinnuo Xu [view email] [v1] Mon, 27 Jul 2026 16:42:36 UTC (20,546 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed, by Xinnuo Xu and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-07

Change to browse by:

cs cs.AI

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?)