Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting
This paper evaluates content moderation configurations using end-to-end metrics Usefulness and Harmful Exposure, comparing Input-only, Response-only, and Input+response hard blocking on product and public datasets. Response-only achieves highest filter-only Usefulness, while Input+response yields lower Harmful Exposure. Replacing Response-only blocking with Response+rewrite recovers most blocked traffic without increasing harmful exposure. Probe routing substantially reduces latency compared to LLM routing. Rewrites balance filter passage and usefulness by generalizing triggering language, but may omit safety-supporting info in sensitive domains.
-->
[Submitted on 28 Jul 2026]
Title:Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting
View a PDF of the paper titled Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting, by Mengya Hu and 7 other authors
View PDF HTML (experimental)
Abstract:Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evaluate these choices using two end-to-end customer-outcome metrics rather than component accuracy: Usefulness, the fraction of turns with a shown, non-harmful, relevant response, and Harmful Exposure, the fraction with a shown harmful response. Latency and error rates are diagnostics. We compare Input only, Response only, and Input + response hard blocking on a human-labelled product benchmark and public ToxicChat evaluation. At the evaluated operating points, Response only achieves the highest filter-only Usefulness in both settings, while Input + response achieves lower Harmful Exposure. Replacing Response only blocking with Response + rewrite recovers most blocked traffic and yields the same observed Harmful Exposure count as Response only blocking for the selected configuration; this equality is not an equivalence result. Probe routing substantially reduces conditional route-and-generation time relative to LLM routing at comparable measured outcomes. A focused output review shows how rewrites balance filter passage with usefulness by generalizing triggering language while retaining benign intent and safe redirection; some sensitive-domain outputs nevertheless omit potentially safety-relevant support information. These results support comparing moderation configurations under deployment-specific safety and latency constraints rather than applying a universal placement rule. Code and public artifacts are available at this https URL
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2607.26200 [cs.CL]
(or arXiv:2607.26200v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.26200
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Mengya Hu [view email] [v1] Tue, 28 Jul 2026 19:05:24 UTC (379 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting, by Mengya Hu and 7 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-07
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?)