Hugging Face Daily Papers · · 5 min read

LLM-based Detection of Manipulative Political Narratives

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context.<br>To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing.<br>The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters.<br>Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.</p>\n","updatedAt":"2026-05-15T02:10:18.303Z","author":{"_id":"64b3fc1fa24816979609dcb3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b3fc1fa24816979609dcb3/cHRMs4YegRcgbZO8_bBaZ.jpeg","fullname":"Sinclair Schneider","name":"SinclairSchneider","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":16,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.908058762550354},"editors":["SinclairSchneider"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64b3fc1fa24816979609dcb3/cHRMs4YegRcgbZO8_bBaZ.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.14354","authors":[{"_id":"6a067829b1a8cbabc9f097eb","name":"Sinclair Schneider","hidden":false},{"_id":"6a067829b1a8cbabc9f097ec","name":"Florian Steuber","hidden":false},{"_id":"6a067829b1a8cbabc9f097ed","name":"Gabi Dreo Rodosek","hidden":false}],"publishedAt":"2026-05-14T00:00:00.000Z","submittedOnDailyAt":"2026-05-15T00:00:00.000Z","title":"LLM-based Detection of Manipulative Political Narratives","submittedOnDailyBy":{"_id":"64b3fc1fa24816979609dcb3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b3fc1fa24816979609dcb3/cHRMs4YegRcgbZO8_bBaZ.jpeg","isPro":false,"fullname":"Sinclair Schneider","user":"SinclairSchneider","type":"user","name":"SinclairSchneider"},"summary":"We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context.\n To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing.\n The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters.\n Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.","upvotes":2,"discussionId":"6a067829b1a8cbabc9f097ee","githubRepo":"https://github.com/SinclairSchneider/manipulative_narrative_detection","githubRepoAddedBy":"user","ai_summary":"A computational framework combining prompt-based filtering and unsupervised clustering identifies manipulative political narrative clusters from social media posts without requiring predefined categories.","ai_keywords":["few-shot prompt","UMAP","HDBSCAN","unsupervised clustering","prompt-based filtering"],"githubStars":1,"organization":{"_id":"64d03866d8d0927372c55759","name":"NLP-UniBW","fullname":"NLP Research Group UniBW","avatar":"https://www.gravatar.com/avatar/b63d9982feef408a456b1acfacb657c0?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"661ab1f1fa3b144a381fa454","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661ab1f1fa3b144a381fa454/IlpZBb9NCjo7ntFwMIH53.png","isPro":true,"fullname":"Urro","user":"urroxyz","type":"user"},{"_id":"645ac130c4acfcf664028c73","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/645ac130c4acfcf664028c73/NRC-VoJcLVVFvuU6dd-AQ.jpeg","isPro":false,"fullname":"John Giles III","user":"maxnumbers","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"64d03866d8d0927372c55759","name":"NLP-UniBW","fullname":"NLP Research Group UniBW","avatar":"https://www.gravatar.com/avatar/b63d9982feef408a456b1acfacb657c0?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.14354.md"}">
Papers
arxiv:2605.14354

LLM-based Detection of Manipulative Political Narratives

Published on May 14
· Submitted by
Sinclair Schneider
on May 15
Authors:
,
,

Abstract

A computational framework combining prompt-based filtering and unsupervised clustering identifies manipulative political narrative clusters from social media posts without requiring predefined categories.

AI-generated summary

We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context. To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing. The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters. Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.

Community

We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context.
To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing.
The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters.
Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.14354
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.14354 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.14354 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.14354 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers