A study of sequence weighting at scale: Jane Street
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Jane Street researchers studied how language models learn from individually weighted training sequences across model sizes, from tens of millions to hundreds of billions of parameters, using in-house models and the open-weight Qwen 2.5 family.