Skip to content
AI News HubLIVE
Original source2 min read

Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs

Summary

A new paper introduces a validity-diversity framework showing that diversity collapse in LLMs stems from two forms of miscalibration during decoding: order calibration (valid tokens not reliably ranked above invalid) and shape calibration (probability mass over-concentrated on few valid tokens). Experiments across 14 models confirm that diversity issues are not just sampling heuristic flaws but fundamental calibration problems.

SourcearXiv Computational LinguisticsAuthor: Amin Banayeeanzade, Qingchuan Yang, Dhruv Tarsadiya, Fatemeh Bahrani, Leonardo Blas, Alfy Samuel, Robin Jia, Meisam Razaviyayn, Sai Praneeth Karimireddy
Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2605.11128] Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs

[Submitted on 11 May 2026]

Title:Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs

View a PDF of the paper titled Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs, by Amin Banayeeanzade and 8 other authors

View PDF HTML (experimental)

Abstract:Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible outputs. While prior work has developed benchmarks for measuring this lack of diversity, less is known about how the step-by-step probability distributions at inference time cause the problem. We introduce a validity--diversity framework that attributes diversity collapse to how an LLM allocates probability mass across valid and invalid continuations during decoding. This framework decomposes the bottleneck into two complementary forms of miscalibration. First, order calibration: valid tokens are not reliably ranked above invalid tokens, so rank-based cutoff rules must trade off between recovering valid continuations and admitting invalid ones. Second, shape calibration: probability mass is overly concentrated only on few valid continuations while having a heavy-tail of mixed valid and invalid tokens, so maintaining high validity limits diversity. We formalize both mechanisms and show that local failures compound across decoding steps, producing strong sequence-level losses in diversity. Empirically, we develop controlled diagnostics for probing these bottlenecks, including tasks with exactly known valid sets and oracle cutoff baselines. Across 14 language models spanning multiple families and scales, we find that diversity collapse is not merely a limitation of particular sampling heuristics, but a consequence of order and shape miscalibration in the LLM distribution.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2605.11128 [cs.CL]

(or arXiv:2605.11128v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.11128

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qingchuan Yang [view email] [v1] Mon, 11 May 2026 18:36:30 UTC (1,387 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs, by Amin Banayeeanzade and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • LLMs suffer from diversity collapse, often producing a narrow set of outputs.
  • The paper identifies two types of miscalibration: order and shape calibration.
  • Local miscalibration compounds across decoding steps, leading to severe sequence-level diversity loss.
  • Experiments on 14 models show that diversity collapse is inherent to the model distribution, not just sampling methods.

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

More recent stories on this topic · Models