Experimental browser for the Atmosphere
To researchers doing LLM evaluation: prompting is *not a substitute* for direct probability measurements. Check out the camera-ready version of our work, to appear at EMNLP 2023! (w/ @rplevy.bsky.social) Paper: arxiv.org/abs/2305.13264 Original thread: twitter.com/_jennhu/stat...
Oct 24, 2023, 3:03 PM
{ "uri": "at://did:plc:t7jbj4w3uo2sus4bc3znsspa/app.bsky.feed.post/3kciylu4bpi2w", "cid": "bafyreiclw56tvjjsi4r5tv53erbkmmzwjf4ohc2rttnowg6tivm4k7cdfi", "value": { "text": "To researchers doing LLM evaluation: prompting is *not a substitute* for direct probability measurements. Check out the camera-ready version of our work, to appear at EMNLP 2023! (w/ @rplevy.bsky.social) \n\nPaper: arxiv.org/abs/2305.13264\n\nOriginal thread: twitter.com/_jennhu/stat...", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.images", "images": [ { "alt": "", "image": { "$type": "blob", "ref": { "$link": "bafkreihyglraolye6tocackpu4npdfprzqleyytjugxvqfe6gnzkexu3re" }, "mimeType": "image/jpeg", "size": 473502 }, "aspectRatio": { "width": 1143, "height": 2000 } } ] }, "langs": [ "en" ], "facets": [ { "$type": "app.bsky.richtext.facet", "index": { "byteEnd": 202, "byteStart": 183 }, "features": [ { "did": "did:plc:euj7iyh64dxgizzj5sapymjc", "$type": "app.bsky.richtext.facet#mention" } ] }, { "index": { "byteEnd": 237, "byteStart": 213 }, "features": [ { "uri": "https://arxiv.org/abs/2305.13264", "$type": "app.bsky.richtext.facet#link" } ] }, { "index": { "byteEnd": 283, "byteStart": 256 }, "features": [ { "uri": "https://twitter.com/_jennhu/status/1660751904920485888", "$type": "app.bsky.richtext.facet#link" } ] } ], "createdAt": "2023-10-24T15:03:19.412Z" } }