MétaCan
Menu
Back to cohort
Record W4416553095 · doi:10.1609/aaaiss.v7i1.36916

MedPerturbing LLMs: A Comparative Study of Toxicity, PromptTuning, and Jailbreaks in Medical QA

2025· article· W4416553095 on OpenAlexafffund
Amirreza Naziri, Laleh Seyyed-Kalantari

Bibliographic record

VenueProceedings of the AAAI Symposium Series · 2025
Typearticle
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsVector Institute
FundersNatural Sciences and Engineering Research Council of CanadaCanada First Research Excellence Fund
KeywordsSoftware deploymentVulnerability (computing)Guard (computer science)Adversarial systemKey (lock)Risk assessmentBaseline (sea)Risk management

Abstract

fetched live from OpenAlex

Large Language Models (LLMs) are increasingly adopted across domains, including sensitive areas such as healthcare. However, their deployment raises significant safety concerns, particularly with respect to toxicity. In this paper, we evaluate the toxicity of widely used general-purpose LLMs in medical question–answering tasks. We investigate three complementary scenarios: (i) baseline querying, (ii) prompt guidelines designed to mitigate toxic outputs, and (iii) adversarial jailbreak prompting intended to elicit harmful content. To measure toxicity, we apply three established metrics to five LLMs ranging from 2B to 9B parameters, using MedPerturb, a dataset of medical questions systematically perturbed across gender, race, and age. Our results show that while carefully crafted guidelines can reduce toxic outputs and mitigate demographic biases, adversarial instructions are highly effective at bypassing safety mechanisms. Our evaluation reveals that all models exhibit limited resilience to jailbreak attacks, highlighting a critical vulnerability that restricts their safe deployment in clinical contexts. By answering three key questions—(1) what levels of toxicity these models exhibit in standard medical scenarios, (2) how far prompt tuning can reduce toxicity, and (3) how vulnerable they are to jailbreaks, our study provides a structured assessment of the risks and limitations of LLMs in healthcare, and shows the importance of establishing robust guidelines and protections to promote the safe deployment of LLMs in healthcare and to guard against harmful misuse.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.553
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.065
GPT teacher head0.385
Teacher spread0.321 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designQualitative
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the AAAI Symposium SeriesSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207