Knowledge is a Region in Weight Space for Fine-tuned Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2302.04863/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTKnowledge is a Region in Weight Space for Fine-tuned Language Models — mentioned by macleginnhttps://news.ycombinator.com/item?id=38760653urn:hackerpapers:mention:2302.04863:38760653Mon, 25 Dec 2023 07:47:06 GMT<p>This also generalises: https://arxiv.org/abs/2302.04863</p><p><a href="https://hackerpaper.kaipfister.de/p/2302.04863/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGKnowledge is a Region in Weight Space for Fine-tuned Language Models — HN submissionhttps://news.ycombinator.com/item?id=34905471urn:hackerpapers:submission:2302.04863:34905471Thu, 23 Feb 2023 01:07:34 GMT<p>Knowledge is a region in weight space for fine-tuned language models</p><p></p><p>84 points; 24 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2302.04863/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG