ATProto Browser

Experimental browser for the Atmosphere

Post

How do language models generalize from information they learn in-context vs. via finetuning? In arxiv.org/abs/2505.00661 we show that in-context learning can generalize more flexibly, illustrating key differences in the inductive biases of these modes of learning — and ways to improve finetuning. 1/

May 2, 2025, 5:02 PM

Loading post...

Record data

{
  "uri": "at://did:plc:5llt5pj7sjira7v5jm3rcv2g/app.bsky.feed.like/3loa2efml3y2c",
  "cid": "bafyreidlxwpe5ssisowejwt4byqd3spfqpslquy5hcqjlenry37opqskq4",
  "value": {
    "$type": "app.bsky.feed.like",
    "subject": {
      "cid": "bafyreic2lwnt3zuft7p2tallt4oy7ldiqbzlpmtxiqikpliy5hhsqgwbmu",
      "uri": "at://did:plc:e6ewzleebkdi2y2bxhjxoknt/app.bsky.feed.post/3lo7ci4russ2s"
    },
    "createdAt": "2025-05-03T00:09:30.969Z"
  }
}