https://hackerpaper.kaipfister.de/p/2311.04954/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=41844127urn:hackerpapers:mention:2311.04954:41844127Tue, 15 Oct 2024 01:46:48 GMT<p>Could you share some of those papers? I had a great discussion with Marc Fischer from the LMQL team [0] on this topic while at ICML earlier this year. Their work recommended decoding to natural language templates with mad lib-style constraints to follow that “happy path” you refer to, instead of decoding to a (relatively more specific latent) JSON schema [1]. Since you provided a template and knew the targeted tokens for generation you could strip your structured content out of the message. This technique also allowed for beam search where you can optimize tokens which lead to the tokens…</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.04954/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL