Construct · 1 fields · 1 citations

prompt format sensitivity: 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

large swings in language model accuracy caused by meaning-preserving changes to prompt formatting such as separators and spacing.

In natural language processing, prompt format sensitivity refers to large swings in language model accuracy caused by meaning-preserving changes to prompt formatting such as separators and spacing. This meaning comes from Sclar (2023) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how prompt format sensitivity 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 model3 fields · 3 citationsjingle · one word, three constructs natural3 fields · 7 citationsjingle · one word, three constructs

References

Sclar, M., Choi, Y., Tsvetkov, Y., & Suhr, A. (2023). Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. arXiv. https://doi.org/10.48550/arxiv.2310.11324

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