[2504.17999] Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Human-Computer Interaction

arXiv:2504.17999 (cs)

[Submitted on 25 Apr 2025 (v1), last revised 23 Jul 2025 (this version, v2)]

Title:Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving

Authors:Chang Xiao, Brenda Yang<br>View a PDF of the paper titled Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving, by Chang Xiao and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated with the content. This mismatch frequently leads to inefficient use of computational resources. For example, in cloud-based services, streaming content faster than users can read appears unnecessary, resulting in wasted computational resources and potential delays for other users, particularly during peak usage periods. To address this issue, we propose an adaptive streaming method that dynamically adjusts the pacing of LLM streaming output in real-time based on inferred cognitive load. Our approach estimates the cognitive load associated with streaming content and strategically slows down the stream during complex or information-rich segments, thereby freeing computational resources for other users. We conducted a statistical analysis and simulation based on a statistical model derived from data collected in a crowdsourced user study across various types of LLM-generated content. Our results show that this adaptive method can effectively reduce computational consumption while largely maintaining streaming speed above user's normal reading speed.

Subjects:

Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)

Cite as:<br>arXiv:2504.17999 [cs.HC]

(or<br>arXiv:2504.17999v2 [cs.HC] for this version)

https://doi.org/10.48550/arXiv.2504.17999

Focus to learn more

arXiv-issued DOI via DataCite

Journal reference:<br>The 38th Annual ACM Symposium on User Interface Software and Technology (UIST 25), September 28-October 01, 2025, Busan, Republic of Korea

Related DOI:

https://doi.org/10.1145/3746059.3747721

Focus to learn more

DOI(s) linking to related resources

Submission history<br>From: Chang Xiao [view email]<br>[v1]<br>Fri, 25 Apr 2025 00:58:37 UTC (3,225 KB)

[v2]<br>Wed, 23 Jul 2025 18:50:43 UTC (3,237 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving, by Chang Xiao and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.HC

next >

new<br>recent<br>| 2025-04

Change to browse by:

cs<br>cs.LG

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from