https://hackerpaper.kaipfister.de/p/2305.10266/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=38574712urn:hackerpapers:mention:2305.10266:38574712Fri, 08 Dec 2023 21:29:29 GMT<p>&gt;Only if it was trained on a corpus of existing translations. Not Necessary. Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM&#x27;s Translation Capability (https://arxiv.org/abs/2305.10266) ablation studies performed on the effects of removing tiers of multilingual corpora (parallel corpora, bilingual (not necessarily parallel), and english only) Removing Parallel corpora or even just bilingual data in general reduces quality but does not make the model unable to translate. Crucially, the gap or reduction in quality also seems to diminish with scale. The paper…</p><p><a href="https://hackerpaper.kaipfister.de/p/2305.10266/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL