AI News HubLIVE
Original source2 min read

PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts

This paper proposes PromptNCE, which estimates pointwise mutual information (PMI) zero-shot using only LLMs and prompts, avoiding the need for task-specific critics. It achieves Spearman correlation up to 0.82 on three datasets and demonstrates applicability in low-data educational settings.

SourcearXiv Computational LinguisticsAuthor: Juliette Woodrow, Chris Piech

[2605.21776] PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts

[Submitted on 20 May 2026]

Title:PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts

View a PDF of the paper titled PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts, by Juliette Woodrow and 1 other authors

View PDF HTML (experimental)

Abstract:Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using only prompts and elicited probabilities. We introduce a benchmark with human-derived ground-truth PMI across three publicly available datasets, and evaluate five information-theoretic prompting-based estimators. Our main method, PromptNCE, frames conditional probability estimation as a contrastive task and augments the candidate set with an explicit OTHER category. We show theoretically that adding OTHER recovers the true conditional P(y | x) rather than just a ranking over listed candidates, turning a contrastive prompt into a general-purpose zero-shot probability estimator. PromptNCE is the best zero-shot method on all three datasets, reaching Spearman correlation up to 0.82 with human-derived PMI. We also present a case study in computer science education showing how these estimators can be used to score student knowledge summaries in a low-data setting.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2605.21776 [cs.CL]

(or arXiv:2605.21776v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.21776

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Juliette Woodrow [view email] [v1] Wed, 20 May 2026 22:10:54 UTC (197 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled PromptNCE: Pointwise Mutual Information Predictions Using Only LLMs and Contrastive Estimation Prompts, by Juliette Woodrow and 1 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?)