The Effect of Sampling Temperature on Problem Solving in Large Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2402.05201/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTThe Effect of Sampling Temperature on Problem Solving in Large Language Models — mentioned by phirehttps://news.ycombinator.com/item?id=39958125urn:hackerpapers:mention:2402.05201:39958125Sun, 07 Apr 2024 04:06:34 GMT<p>I found this other paper that tests Temperature: https://arxiv.org/abs/2402.05201 It appears that temperature has no impact on problem solving performance. So this paper isn&#x27;t getting improved performance because the token for the correct answer is more probable. My theory is that the multiple queries are allowing the whole probability space of possible answers to be sampled. Not just the probabilities of the most likely output token, but the probabilities of all possible internal model states. And sampling that probability space of the whole model state and finding the average is a very…</p><p><a href="https://hackerpaper.kaipfister.de/p/2402.05201/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL