MétaCan
Menu
Back to cohort
Record W3099434687 · doi:10.18653/v1/2020.conll-1.26

“LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently

2020· preprint· en· W3099434687 on OpenAlexfundno aff
Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldSocial Sciences
TopicLanguage and cultural evolution
Canadian institutionsnot available
FundersAgence Nationale de la RechercheCanadian Institute for Advanced ResearchMicrosoft Research
KeywordsZipf's lawComputer scienceChannel (broadcasting)Artificial neural networkNatural (archaeology)Artificial intelligenceTheoretical computer scienceComputer networkMathematics

Abstract

fetched live from OpenAlex

Previous work has shown that artificial neural agents naturally develop surprisingly nonefficient codes.This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length.Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages.Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified.We hence introduce a new communication system, "Laz-Impa", where the speaker is made increasingly lazy, i.e., avoids long messages, and the listener impatient, i.e., seeks to guess the intended content as soon as possible.

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)0.001
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation 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 score0.003
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.009
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.002
Scholarly communication0.0010.003
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.001

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 head0.074
GPT teacher head0.362
Teacher spread0.288 · 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 designSimulation or modeling
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

Citations15
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicLanguage and cultural evolutionFrench-language works237,207