Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

arxiv.org

Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

arxiv.org

ray@lemmy.ml to Wikimedia@lemmy.mlEnglish · 3 years ago

You must log in or # to comment.

Chat

Wikimedia@lemmy.ml

wikimedia@lemmy.ml

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !wikimedia@lemmy.ml

Wiki-pedia, -tionary, -source, -books, -quote, commons, -versity, -voyage, -news, -data, -species.

Civility is aggressively enforced: do not be rude, troll-y, flame-bait-y, etc. If someone else is, please report, block as necessary, and move on.

Comments that cannot reasonably lead to discussion or which have no analysis (“first!”, “lol”, [string of emojis]) will be deleted. Please do not post them.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

5 users / day
5 users / week
5 users / month
5 users / 6 months
1 local subscriber
149 subscribers
5 Posts
0 Comments
Modlog