https://hackerpaper.kaipfister.de/p/2204.03084/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=37313635urn:hackerpapers:mention:2204.03084:37313635Tue, 29 Aug 2023 20:36:20 GMT<p>True. This is an open area of research. Tools like guidance (or other implementations of constrained decoding with llms [1,2]) will likely help improve this problem. [1] A guidance language for controlling large language models. https://github.com/guidance-ai/guidance [2] Knowledge Infused Decoding https://arxiv.org/abs/2204.03084</p><p><a href="https://hackerpaper.kaipfister.de/p/2204.03084/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL