MétaCan
Menu
Back to cohort
Record W6947849807 · doi:10.48448/zkhk-xm79

EvoGrad: An Online Platform for an Evolving Winograd Schema Challenge using Adversarial Human Perturbations

2022· other· en· W6947849807 on OpenAlexaff

Bibliographic record

VenueUnderline Science Inc. · 2022
Typeother
Languageen
FieldEarth and Planetary Sciences
TopicEvolution and Paleontology Studies
Canadian institutionsMcGill UniversityBrock University
Fundersnot available
KeywordsAdversarial systemSchema (genetic algorithms)Task (project management)Metric (unit)Stability (learning theory)Measure (data warehouse)

Abstract

fetched live from OpenAlex

Transformer-based language models have been recently showcasing impressive performance on a number of common-sense reasoning tasks such as the Winograd Schema Challenge (WSC) while continuing to struggle on task instances that are either slightly re-worded or perturbed. In the following paper, we wish to address these issues by re-framing the WSC using a never-ending learning, human-in-the-loop scenario devised specifically for perturbed pronoun co-reference resolution problems. We introduce EvoGrad, an open-source, user-friendly platform for the continual evaluation and development of models, based on iterations of human-adversarial perturbations. Given that common-sense knowledge varies cross-culturally and through time, our platform allows for the communal contribution towards an evolving task that is both inclusive and accessible to wider societies. In addition, we propose a novel mechanism to develop new task instances, and define a new metric to measure model stability on such dynamic tasks, called the Minimum Error Depth. We show that models fine-tuned on a small iteration of EvoGrad have their performance boosted on WSC-based tasks; this indicates a promising synergy between the acquisition of common sense and the never-ending learning paradigm.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.817
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0020.001
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0070.000

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 head0.150
GPT teacher head0.341
Teacher spread0.191 · 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 designObservational
Domainnot available
GenreOther

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
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueUnderline Science Inc.Same topicEvolution and Paleontology StudiesFrench-language works237,207