Mix Your Base and RLVR Weights: A Training-Free Knob for Diversity
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
Youngseong Kim, an independent researcher, reports that RLVR-trained language models gain single-sample accuracy (pass@1) but lose sample diversity (pass@k at large k).