MétaCan
Menu
Back to cohort
Record W4416445260 · doi:10.48550/arxiv.2505.03563

Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework

2025· preprint· en· W4416445260 on OpenAlexfundno aff
Cléa Chataigner, R. Ma, Prakhar Ganesh, Y. Chen, Afaf Taïk, Elliot Creager, Golnoosh Farnadi

Bibliographic record

VenueArXiv.org · 2025
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
FundersFonds de recherche du Québec – Nature et technologiesCompute CanadaCanadian Institute for Advanced Research
KeywordsAuditQuality (philosophy)Natural languageStrengths and weaknessesNatural (archaeology)Language modelSemantics (computer science)

Abstract

fetched live from OpenAlex

Large language models (LLMs) are highly sensitive to subtle changes in prompt phrasing, posing challenges for reliable auditing. Prior methods often apply unconstrained prompt paraphrasing, which risk missing linguistic and demographic factors that shape authentic user interactions. We introduce AUGMENT (Automated User-Grounded Modeling and Evaluation of Natural Language Transformations), a framework for generating controlled paraphrases, grounded in user behaviors. AUGMENT leverages linguistically informed rules and enforces quality through checks on instruction adherence, semantic similarity, and realism, ensuring paraphrases are both reliable and meaningful for auditing. Through case studies on the BBQ and MMLU datasets, we show that controlled paraphrases uncover systematic weaknesses that remain obscured under unconstrained variation. These results highlight the value of the AUGMENT framework for reliable auditing.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.013
metaresearch head score (Gemma)0.088
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.013
Threshold uncertainty score0.071

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.088
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0050.007
Open science0.0030.006
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0030.003

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 head0.045
GPT teacher head0.291
Teacher spread0.246 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
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 routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicTopic ModelingFrench-language works237,207