MétaCan
Menu
Back to cohort
Record W4389095096 · doi:10.26434/chemrxiv-2023-r1qn9

Diagram-based Input for Large Language Models to Support Accessible STEM Learning

2023· preprint· en· W4389095096 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueChemRxiv · 2023
Typepreprint
Languageen
FieldSocial Sciences
TopicDigital Accessibility for Disabilities
Canadian institutionsDow Chemical (Canada)
FundersNational Science Foundation
KeywordsInterfacingComputer scienceUsabilityDiagramHuman–computer interactionProgramming languageDatabase

Abstract

fetched live from OpenAlex

To meet the accessibility needs of students who are blind or have low vision (BLV), detailed textual descriptions of STEM diagrams within interactive learning tools are cre-ated in real-time and correspond to the configurations of the interactive software system. The descriptions are read by screen readers as alternative (alt) text to provide infor-mation for BLV students to compose mental representa-tions of the diagram. These descriptions provide a unique bridge from the visual language of STEM diagrams to natural language of Large Language Models (LLMs). By interfacing with an LLM, these descriptions are used for personalized exploration by the BLV user and to guide all learners through a defined pedagogical pathway. Results from a usability study with four BLV adults are reported.

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.

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)0.002
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 score0.339
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
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 head0.117
GPT teacher head0.377
Teacher spread0.260 · 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