Skip to content
AI News HubLIVE
Original source2 min read

LLM Hallucination Detection via Low-rank Multilinear Decomposition

Summary

Researchers present LOTUS, a multilinear low-rank decomposition framework that extracts compact representations from LLM hidden states and trains a lightweight classifier to detect hallucinations, outperforming recent state-of-the-art baselines across multiple models and QA benchmarks.

SourcearXiv Computational LinguisticsAuthor: Devansh Sharma, Faizul Rakib Sayem, Shahana Ibrahim
LLM Hallucination Detection via Low-rank Multilinear Decomposition
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 26 Oct 2026]

Title:LLM Hallucination Detection via Low-rank Multilinear Decomposition

View a PDF of the paper titled LLM Hallucination Detection via Low-rank Multilinear Decomposition, by Devansh Sharma and 2 other authors

View PDF HTML (experimental)

Abstract:Large language models (LLMs) frequently generate fluent yet factually incorrect responses, raising concerns about their reliability. Recent hallucination detectors increasingly exploit internal representations, but extracting informative signals from high-dimensional hidden states remains challenging. Existing approaches often rely on selected activations or pooling-based compression, potentially overlooking discriminative information distributed across Transformer layers, feature modes, and tokens. We propose LOTUS (Low-rank Order-statistic TUcker-based Subspace learning), a multilinear low-rank decomposition framework for hallucination detection that extracts compact representations from LLM hidden states while reducing dependence on labeled data. Our approach first summarizes variable-length token representations using complementary statistical descriptors that capture peak activations, activation distributions, and cross-layer changes. We then leverage low-rank multilinear decomposition to extract compact representations that capture the underlying structure of LLM hidden states, which are subsequently used to train a lightweight hallucination classifier. Experiments across multiple LLMs and question-answering benchmarks demonstrate improved hallucination detection performance over recent state-of-the-art baselines.

Comments: 26 pages, 3 figures. Code: this https URL

Subjects:

Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as: arXiv:2610.36191 [cs.CL]

(or arXiv:2610.36191v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2610.36191

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Devansh Sharma [view email] [v1] Mon, 26 Oct 2026 19:24:13 UTC (349 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled LLM Hallucination Detection via Low-rank Multilinear Decomposition, by Devansh Sharma and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-10

Change to browse by:

cs cs.LG

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?)

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

  • LOTUS summarizes variable-length token representations with complementary statistical descriptors capturing peak activations, activation distributions, and cross-layer changes.
  • Low-rank multilinear decomposition extracts compact, structured representations from hidden states while reducing dependence on labeled data.
  • Experiments across multiple LLMs and question-answering benchmarks show improved hallucination detection over recent state-of-the-art baselines.
  • The 26-page paper with 3 figures provides code and spans cs.CL and cs.LG.

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

More recent stories on this topic · Models