Construct · 1 fields · 1 citations

attention sinks: 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

initial tokens that draw a large share of attention in language models regardless of meaning, which matters for streaming long inputs.

In natural language processing, attention sinks refers to initial tokens that draw a large share of attention in language models regardless of meaning, which matters for streaming long inputs. This meaning comes from Xiao (2023) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how attention sinks 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

attention5 fields · 10 citationsjingle · one name, five constructs natural3 fields · 7 citationsjingle · one word, three constructs share2 fields · 2 citationsjingle · one word, two constructs

References

Xiao, G., Tian, Y., Chen, B., Han, S., & Lewis, M. (2023). Efficient Streaming Language Models with Attention Sinks. arXiv. https://doi.org/10.48550/arxiv.2309.17453

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