Construct · 1 fields · 1 citations

embers of autoregression: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Natural language processing

the view that language models carry traces of next-word prediction, so their accuracy depends on how probable the task, input and output are.

In natural language processing, embers of autoregression refers to the view that language models carry traces of next-word prediction, so their accuracy depends on how probable the task, input and output are. This meaning comes from McCoy (2023) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how embers of autoregression sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

accuracy3 fields · 6 citationsjingle · one word, three constructs carry1 fields · 1 citationsanchor · a standalone construct natural3 fields · 7 citationsjingle · one word, three constructs

References

McCoy, R. T., Yao, S., Friedman, D., Hardy, M., & Griffiths, T. L. (2023). Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve. arXiv. https://doi.org/10.48550/arxiv.2309.13638

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct