[2606.06203] Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

-->

Computer Science > Computation and Language

arXiv:2606.06203 (cs)

[Submitted on 4 Jun 2026]

Title:Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

Authors:Giovanni Dettori, Matteo Boffa, Danilo Giordano, Idilio Drago, Marco Mellia<br>View a PDF of the paper titled Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs, by Giovanni Dettori and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study lexical density -- the rate at which a context introduces distinct information -- as a third, largely overlooked factor that systematically reduces the effective context window of LLMs. We quantify the impact of lexical density on open-weight LLMs (9B-685B) using three "find-the-needle" style benchmarks with identical length (~12k tokens) and controlled needle position, but increasing density of information. We observe a sharp performance collapse in higher-density benchmarks: models that are near-perfect in sparse contexts drop below 60% retrieval score on denser ones. To rule out task-type confounds, we vary and control the density within each benchmark while keeping all other properties unchanged. Reducing density generally restores performance, especially in the high-density regimes where degradation appears. These results show that effective context capacity is a function of lexical density, with direct implications for real-world LLM systems operating on compact, information-rich inputs.

Comments:<br>20 pages, 6 figures

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2606.06203 [cs.CL]

(or<br>arXiv:2606.06203v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.06203

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Giovanni Dettori [view email]<br>[v1]<br>Thu, 4 Jun 2026 14:08:30 UTC (549 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs, by Giovanni Dettori and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.AI

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?)