Skip to content
AI News HubLIVE
Original source2 min read

RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs

Summary

Researchers introduce RAW, a method that uses LLM stochasticity as a natural experiment to causally measure how refusals affect user re-engagement from existing logs; across 15 deployed models, about half show a 3–17 pp re-engagement cost per refusal, at roughly $0.30 per 1,000 conversations.

SourcearXiv Computational LinguisticsAuthor: Pavel Kireyev
RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs
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 25 Sep 2026]

Title:RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs

View a PDF of the paper titled RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs, by Pavel Kireyev

View PDF HTML (experimental)

Abstract:Deployed LLMs field hundreds of millions of conversations a day and refuse a non-trivial fraction of user requests, yet the user-side cost of refusal, whether users disengage and by how much, is unmeasured on any production model: a blind spot for the consumer-facing platforms built on them. A/B-testing refusal is ethically and operationally constrained on frontier-lab products and unavailable to third-party platforms deploying these models through a fixed API. We introduce RAW, a method that uses LLM stochasticity as a natural experiment: at near-identical prompts in any existing log, the same model sometimes refuses and sometimes does not, and that variation identifies the causal user-side effect of refusal. Applying the method to 15 deployed LLMs in LMSYS-Chat-1M and WildChat, with user-clustered inference, we find that for about half of the models we can measure precisely, a refusal costs 3 to 17 pp of subsequent re-engagement; the rest show no distinguishable effect, among them one deployment whose positive point estimate we trace to persistent users retrying the refused request. Our contribution is the measurement method, which runs on any deployed model from logs alone for about \$0.30 per 1,000 conversations. We release labels, moderation scores, prompt embeddings, and pipeline code.

Comments: Accepted to the EMNLP 2026 Industry Track. 26 pages incl. appendices, 8 figures, 11 tables. Code: this https URL Data: this https URL

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); General Economics (econ.GN)

Cite as: arXiv:2611.21641 [cs.CL]

(or arXiv:2611.21641v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.21641

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Pavel Kireyev [view email] [v1] Fri, 25 Sep 2026 18:55:32 UTC (1,899 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs, by Pavel Kireyev

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI cs.HC econ econ.GN q-fin q-fin.EC

References & Citations

SciX

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

EngineersAdvanced

Key points

  • RAW exploits near-identical prompts where the same model sometimes refuses and sometimes does not, identifying causal user-side effects without A/B testing.
  • Across 15 deployed LLMs in LMSYS-Chat-1M and WildChat, about half of the precisely measurable models show a 3–17 pp drop in subsequent re-engagement after a refusal.
  • The remaining models show no distinguishable effect; one positive estimate is traced to persistent users retrying refused requests.
  • The method runs on logs alone at about $0.30 per 1,000 conversations, with labels, moderation scores, prompt embeddings, and code released.

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