Skip to content
AI News HubLIVE
Original source2 min read

MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering

Summary

MedProb is a lightweight probing framework that answers multiple-choice medical visual question answering (Med-VQA) directly from frozen vision-language model representations, without generating free text. Across PATH-VQA, SLAKE, and VQA-RAD, it recovers substantially more answer-relevant signal than prompting and outperforms medical VLMs and agentic systems. Probing also narrows the apparent gap between small and large models, while free-text generation shows an answer-position bias of up to 10 percentage points.

SourcearXiv Computational LinguisticsAuthor: Erfan Nourbakhsh, Ke Yang, Anthony Rios
MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering
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 3 Sep 2026]

Title:MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering

View a PDF of the paper titled MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering, by Erfan Nourbakhsh and 1 other authors

View PDF HTML (experimental)

Abstract:Medical visual question answering (Med-VQA) is often assumed to require medical fine-tuning, large models, or complex multi-agent pipelines. We revisit this assumption with \textbf{MedProb}, a lightweight probing framework that predicts multiple-choice Med-VQA answers from frozen VLM representations without free-text generation. Across PATH-VQA, SLAKE, and VQA-RAD, MedProb recovers substantially more answer-relevant signal than prompting and performs stronger than medical VLMs and agentic systems. Probing also reduces the apparent gap between small and large models compared to prompting, suggesting that smaller VLMs contain more recoverable Med-VQA signal than generation-based evaluation reveals. Across 14 matched general-purpose and medical VLM pairs, medical adaptation does not consistently improve this linear decodability. Finally, free-text generation exhibits an answer-position bias of up to 10 percentage points, whereas MedProb also has positional bias, however, it is impacted differently than prompting. Our main results target the multiple-choice/multiclass Med-VQA setting; we additionally show the probe can be extended to open-ended generation via a rejection-sampling scoring procedure.

Comments: Accepted to EMNLP Findings 2026

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2609.04336 [cs.CL]

(or arXiv:2609.04336v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.04336

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Anthony Rios [view email] [v1] Thu, 3 Sep 2026 18:04:36 UTC (3,317 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering, by Erfan Nourbakhsh and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • MedProb uses lightweight probes on frozen VLM representations to answer medical multiple-choice visual questions without free-text generation.
  • On PATH-VQA, SLAKE, and VQA-RAD, MedProb beats prompting, medical VLMs, and agentic pipelines.
  • Probing reveals that smaller VLMs contain more recoverable medical QA signal than generation-based evaluation suggests.
  • The paper identifies answer-position bias in generative evaluation and shows MedProb has its own different positional bias.

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