Skip to content
AI News HubLIVE
Original source2 min read

A Model of Diverse Sampling from Language Models

Summary

The paper introduces PoolDPP, which formalizes diverse generation as sampling a size-K subset of complete strings from a determinantal point process (DPP) and approximates it via a finite candidate pool, with a theoretical KL bound decaying as O(1/N). Experiments show improved quality-diversity and precision-recall frontiers on open-ended generation, text-to-SQL, and math reasoning.

SourcearXiv Machine LearningAuthor: Manuel Prada-Corral, Yahya Emara, Timothy J. O'Donnell, Ryan Cotterell, Tim Vieira
A Model of Diverse Sampling from Language Models
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 18 Nov 2026]

Title:A Model of Diverse Sampling from Language Models

View a PDF of the paper titled A Model of Diverse Sampling from Language Models, by Manuel Prada-Corral and 4 other authors

View PDF HTML (experimental)

Abstract:Language models often produce high-quality individual samples but poor sets, with repeated samples clustering around the same semantic modes. We formalize diverse generation as sampling a size-$K$ subset of complete strings from a determinantal point process (DPP), where the likelihood encodes item quality, and the embedding geometry encodes repulsion between similar outputs. Exact inference over all strings is intractable, so we propose PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight the candidates toward the target quality, and run a $K$-DPP sampler on the induced pool kernel; a greedy MAP variant provides deterministic selection. We prove a finite-sample bound with an explicit constant: the KL divergence between the sampler's output and the target $K$-DPP decays as O(1/N) in the pool size. Empirically, PoolDPP extends the quality--diversity frontier on open-ended generation and the precision--recall frontier on ambiguous text-to-SQL (Ambrosia), and on mathematical reasoning (GSM8K), it raises diversity at about the same pass@$K$.

Comments: NeurIPS 2026 paper

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL); Machine Learning (stat.ML)

Cite as: arXiv:2611.25003 [cs.LG]

(or arXiv:2611.25003v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.25003

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Manuel Prada-Corral [view email] [v1] Wed, 18 Nov 2026 17:56:26 UTC (237 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled A Model of Diverse Sampling from Language Models, by Manuel Prada-Corral and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs cs.AI cs.CL cs.FL stat stat.ML

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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

  • Formalizes diverse generation as sampling a size-K subset of complete strings from a DPP, where likelihood encodes quality and embedding geometry encodes repulsion.
  • Proposes PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight toward target quality, and run a K-DPP sampler on the induced pool kernel; a greedy MAP variant gives deterministic selection.
  • Proves a finite-sample bound: KL divergence between sampler output and target K-DPP decays as O(1/N) in pool size.
  • Empirically extends quality-diversity frontier on open-ended generation and precision-recall frontier on text-to-SQL (Ambrosia), and raises diversity at similar pass@K on GSM8K.

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