Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2404.03715/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTDirect Nash Optimization: Teaching Language Models to Self-Improve with General Preferences — HN submissionhttps://news.ycombinator.com/item?id=39972800urn:hackerpapers:submission:2404.03715:39972800Mon, 08 Apr 2024 19:16:54 GMT<p>Direct Nash Optimization: Teaching language models to self-improve</p><p></p><p>52 points; 11 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2404.03715/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG