MétaCan
Menu
Back to cohort

Exploring the intricacies of human memory and its analogous representation in ChatGPT

2024· article· en· W4394006050 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

VenueIndonesian Journal of Electrical Engineering and Computer Science · 2024
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversité de Moncton
Fundersnot available
KeywordsMemorizationRecallComputer scienceParallelsHuman memoryRelevance (law)Representation (politics)Cognitive psychologyMental representationCognitive scienceHuman–computer interactionPsychologyCognitionNeuroscience

Abstract

fetched live from OpenAlex

Human memory and ChatGPT both rely on associations and patterns to generate contextually relevant responses. We explore how they work in tandem. Both use associations to activate related information when prompted. Memory forms generic representations that become precise with added details, similar to ChatGPT's responses with specific prompts. Activation Through Cues: Memory and ChatGPT recall based on cues or prompts, influenced by input. Level of Detail: Memory constructs mental images based on information, just as ChatGPT responds to input details. Dynamic Nature: Both adapt to memorize repeated segments with diverse continuations. By understanding the dynamics of memory and its parallels with ChatGPT's response generation, researchers can further enhance the model's capabilities. Fine-tuning the model's ability to activate relevant information, generate specific responses, and adapt to varying levels of detail and specificity in the input can contribute to its overall performance and relevance in various language tasks.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.912
Threshold uncertainty score0.225

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 studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
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 head0.034
GPT teacher head0.250
Teacher spread0.217 · 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