Measuring remote work using a Large Language Model (LLM)
Bibliographic record
Abstract
Large Language Models (LLMs) can dramatically improve upon traditional text-based measurement tools used by economists We fit, test and train the “Work-from-Home Algorithmic Measure” (WHAM) model to detect new online job postings offering remote/hybrid arrangements. The WHAM model has near-human accuracy. We deploy this model at scale, processing hundreds of millions of job ads collected across five countries and thousands of cities The share of new ads offering remote/hybrid jobs increased four-fold in the US and more than five-fold in the UK, Australia, Canada, and New Zealand, between 2019 and 2023. These data and more are available for researchers at wfhmap.com The “remote work gap” across cities, occupations, and high/low salary workers continues to widen, and the hare of advertised remote/hybrid work is highly skewed towards white-collar workers and cities which are hubs for government, business, technology, and higher education LLMs offer massive potential for empirical research using text data, but one should adhere to best practices and understand the “do’s and don’ts” of these technologies. Generative AI offers immense promise, with some significant limitations
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.005 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".