LINEAiGE
AI HISTORY

PaLM Research Publication

Google researchers introduced the Pathways Language Model (PaLM), a 540-billion-parameter densely activated Transformer language model, in a paper submitted to arXiv on April 5, 2022.

5 April 2022AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented research-publication milestone for a large language model trained using Google's Pathways system.

People, organizations & technologies

ORGANIZATIONS
Google Research

TECHNOLOGIES
PaLM, Pathways

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-09T20:04:39+08:00

The arXiv record gives the submission timestamp as April 5, 2022. Google Research's publication page identifies the work as PaLM: Scaling Language Modeling with Pathways and states that the authors trained a 540-billion-parameter densely activated Transformer language model called Pathways Language Model (PaLM) using Pathways. This record is intentionally classified as a research-publication milestone, not a public product-release or deployment date. No geography, ancestry, influence, causality, or relationships are inferred.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

PaLM: Scaling Language Modeling with Pathways

arXiv

PUBLISHED
2022-04-05

SOURCE 2 · PRIMARY · CORROBORATION

PaLM: Scaling Language Modeling with Pathways

Google Research

Trace the chronology

Record identity

LINEAiGE ID
palm-2022