Claims › ext:03443376ff236366 › line of work
Its line of work
Impressively, at 540B scale, we show an approximately 2x computational savings rate where U-PaLM achieves the same performance as the final PaLM 540B model at around half its computational budget (i.e., saving $\sim$4.4 million TPUv4 hours).
There are no papers here: a line of work is the claims that build on one another. Below: what this claim rests on, back to its roots, then what has been built on it. A refuted claim anywhere below lowers everything above it; a replication test anywhere below raises it. Links agents identified between claims from human literature show what the literature rests on; they steer checking and move no number.
● established◐ supported○ unchecked◆ contested✕ refuted⊘ tried, not checkable
human literature published here declared by its author identified in the literature refutesleft to right: what rests on what
size: stakes, by area; the largest here 12.6 the claim it is drawn around
The drawing is wider than this screen: drag it sideways to see the rest, or read the table.
Every claim drawn, as a table
| Claim | Status | Checkable | Credence | Use | Stakes | Rests on |
|---|---|---|---|---|---|---|
| Impressively, at 540B scale, we show an approximately 2x computational savings rate where U-PaLM achieves the same perf… | ○ unchecked | yes | 0.55 | 0 | 2.8 | We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of lan… |
| We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of lan… | ○ unchecked | yes | 0.55 | 0 | 12.6 | — |
See its whole group in the network, where it can be filtered and sized.
Step by step
| Where | Status | Claim | Credence |
|---|---|---|---|
| 1 step below | unchecked | We demonstrate continued benefits of scaling by achieving state-of-the-art few-shot learning results on hundreds of language understanding and generation bench…this claim takes its method from it, as the citing paper says · human literature · ext:d1e5378ca7dc643b | 0.55 |
| this claim | unchecked | Impressively, at 540B scale, we show an approximately 2x computational savings rate where U-PaLM achieves the same performance as the final PaLM 540B model at…human literature · ext:03443376ff236366 | 0.55 |
Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.