MétaCan
Menu
Back to cohort
Record W4401872841 · doi:10.1016/j.acalib.2024.102942

Comparing generative artificial intelligence tools to voice assistants using reference interactions

2024· article· en· W4401872841 on OpenAlexaff
Amanda Wheatley, Sandy Hervieux

Bibliographic record

VenueThe Journal of Academic Librarianship · 2024
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsMcGill University
Fundersnot available
KeywordsGenerative grammarComputer scienceArtificial intelligenceGenerative modelNatural language processingHuman–computer interaction

Abstract

fetched live from OpenAlex

This study investigates the ability of voice assistants and generative AI tools to respond to reference questions traditionally received by academic librarians. The authors created a sample of 25 questions based on queries received on the virtual reference service at their institution. They then created a rubric to evaluate the quality of the answers that the AI powered tools provided. The authors determined that the tools understand reference questions well and provide relevant answers but that the quality of the references provided, and the accuracy of the answers can be lacking. They suggest that more research needs to be done to understand the place of AI powered tools in reference services.

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)0.022
metaresearch head score (Gemma)0.224
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.022
Threshold uncertainty score0.115

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0220.224
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.002
Science and technology studies0.0010.002
Scholarly communication0.0060.007
Open science0.0020.005
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0040.002

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 head0.340
GPT teacher head0.394
Teacher spread0.054 · 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 designObservational
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

Citations13
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueThe Journal of Academic LibrarianshipSame topicAI in Service InteractionsFrench-language works237,207