Construct · 1 fields · 1 citations

inverse scaling: 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

tasks on which larger language models perform worse than smaller ones, contrary to the usual pattern of gains with scale.

In natural language processing, inverse scaling refers to tasks on which larger language models perform worse than smaller ones, contrary to the usual pattern of gains with scale. This meaning comes from McKenzie (2023) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how inverse scaling 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

natural3 fields · 7 citationsjingle · one word, three constructs pattern4 fields · 5 citationsjingle · one word, four constructs scale3 fields · 3 citationsjingle · one word, three constructs

References

McKenzie, I. R., Lyzhov, A., Pieler, M., Parrish, A., Mueller, A., Prabhu, A., McLean, E., Kirtland, A., Ross, A., Liu, A., Gritsevskiy, A., Wurgaft, D., Kauffman, D., Recchia, G., Liu, J., Cavanagh, J., Weiss, M., Huang, S., Droid, T. F., Tseng, T., Korbak, T., Shen, X., Zhang, Y., Zhou, Z., Kim, N., Bowman, S. R., & Perez, E. (2023). Inverse Scaling: When Bigger Isn't Better. arXiv. https://doi.org/10.48550/arxiv.2306.09479

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