AI News HubLIVE
原文2 min read

CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework

CaVe-VLM-CoT is a modular reflection-based agentic-RAG framework that reduces hallucinations in Vision-Language Models via a five-stage closed-loop pipeline. It introduces a comprehensive 23-metric evaluation suite, anchored by CaVeScore, measuring accuracy, citation precision/recall, attribution, and evidence grounding. Without architectural changes, it achieves 87.1% accuracy on ScienceQA and 55.2% on MMMU.

SourcearXiv AIAuthor: Sneha Rao, Shaina Raza, Dhanesh Ramachandram

[2606.18385] CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework

[Submitted on 16 Jun 2026]

Title:CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework

View a PDF of the paper titled CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework, by Sneha Rao and 2 other authors

View PDF HTML (experimental)

Abstract:Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only partially address this, as they neither enforce step-level citation grounding nor route verification failures back to retrieval for correction. We present CaVe-VLM-CoT, a modular reflection-based agentic-RAG framework that enforces evidence-grounded reasoning through a five-stage closed-loop pipeline: Extractor, Retriever, Solver, Citation Injector, and Verifier, in which detected ungrounded claims trigger structured feedback to the Extractor for targeted re-retrieval. Since no existing framework jointly measures retrieval quality, step-wise citation faithfulness, and cross-modal grounding, we propose a suite of 23 component-wise metrics across all stages, anchored by CaVeScore, a composite metric weighting accuracy, citation precision and recall, attribution, and evidence grounding. Without any architectural or prompt modifications, CaVe-VLM-CoT achieves 87.1\% accuracy and 56.6\% CaVeScore on ScienceQA , and 55.2\% accuracy and 35.7\% CaVeScore on MMMU (30 subjects).

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.18385 [cs.AI]

(or arXiv:2606.18385v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.18385

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sneha Rao [view email] [v1] Tue, 16 Jun 2026 18:28:47 UTC (1,039 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework, by Sneha Rao and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

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?)