Syntactic and semantic control of LLMs via sequential Monte Carlo [pdf] | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Syntactic and semantic control of LLMs via sequential Monte Carlo [pdf] (openreview.net)
		3 points by tanelpoder 9 months ago \| hide \| past \| favorite \| 1 comment

tanelpoder 9 months ago [–]

Discovered this paper via a bit too vague MIT news article [1] Code examples are in their GitHub repo [2]

[1] https://news.mit.edu/2025/making-ai-generated-code-more-accu...

[2] https://github.com/genlm/genlm-control

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact