[Submitted on 15 Oct 2026]
Title:Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss
View a PDF of the paper titled Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss, by Zhiyuan Wang
View PDF HTML (experimental)
Abstract:Running prompt tokens through fewer routed experts during prefill is a simple way to make mixture-of-experts (MoE) serving cheaper, yet it is unclear what this damages. We locate the damage with token-, layer- and attention-path interventions on short-answer question answering in four MoE families. At half the experts the F1 loss of three families is mostly answer form: the model still finds the answer but stops answering briefly. In Qwen3-30B-A3B this loss is made at the two chat-template tokens before the answer, and in DeepSeek-V2-Lite at the first 8-32 prompt tokens, where its instruction sits; by answer likelihood these positions account for about half and a fifth of the damage. Reduction changes the first token's attention mass, norm and largest activation by less than 4%, and restoring super experts or massive activations recovers at most about a quarter of the loss, well below keeping the sensitive positions full. On real prompts with about 4% of tokens at full experts, placing them on the task interface keeps F1 within one point of the unmodified model, while placing them at random in the documents is about 3 points worse (two of five prespecified primary comparisons; the others were undecided or not run). Because the answer boundary always ends a single-turn prompt, and DeepSeek's loss was no longer detectable once its instruction moved away from the start, the sensitive tokens lay at the prompt ends in every sensitive layout we found, so rules that keep the ends are not distinguished from rules that read application marks. Time to first token falls about 14% on 11K-token prompts and not at 2K tokens.
Comments: 8 pages main text, 26 pages with appendices; supplementary material in ancillary files
Subjects:
Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2610.22454 [cs.CL]
(or arXiv:2610.22454v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.22454
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zhiyuan Wang [view email] [v1] Thu, 15 Oct 2026 16:26:07 UTC (509 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss, by Zhiyuan Wang
View PDF
HTML (experimental)
TeX Source
view license
Ancillary-file links:
Ancillary files (details):
supplement.pdf
Additional Features
Audio Summary
Current browse context:
cs.CL
new | recent | 2026-10
Change to browse by:
cs 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?)