Do Long-Range Language Models Actually Use Long-Range Context? · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2109.09115/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDo Long-Range Language Models Actually Use Long-Range Context? — mentioned by skepticATXhttps://news.ycombinator.com/item?id=35502673urn:hackerpapers:mention:2109.09115:35502673Sun, 09 Apr 2023 13:45:00 GMT<p>Can someone with a better understanding than I have comment about the relationship between these results and this paper: https://arxiv.org/abs/2109.09115, which seems to demonstrate that a longer context length has diminishing returns?</p><p><a href="https://hackerpaper.kaipfister.de/p/2109.09115/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL