output diversity
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Oct 2026
3 papers in the last two months, against 0 in the two before.
Start here
The paper to read first- 1Pass@k misses output diversity changes caused by model post-training
pass@k measures correct-answer probability but not output diversity, so it cannot detect post-training's effects on capability breadth.
Oct 2026
How fast it is moving
Often studied with
reinforcement learning with verifiable rewardsReinforcement learning that uses rewards from objectively checkable signals like correct answers or verification feedback.2 togethergroup relative policy optimizationA reinforcement learning method that optimizes policy by computing advantages based on group-level reward statistics.1 togethermechanistic interpretabilityThe study of how neural networks compute through internal circuits, features, and causal interventions, rather than just input-output behavior.1 togetherThe papers
Most central to this idea first, not most recent.
- Academiccs.LG
Pass@k misses output diversity changes caused by model post-training
pass@k measures correct-answer probability but not output diversity, so it cannot detect post-training's effects on capability breadth.
Accenture Strategy & Consulting, Vizuara AI Labs · Oct 2026
- Top Universitycs.CL
Sparse RL-Guided Token Choices Recover Most Math Reasoning Gains
Borrowing the RL model's token at just 4% of positions recovers 90.5% of the RL pass@1 gain on AIME problems.
University of California, San Diego, Meituan, LongCat Team · Oct 2026
- Big Techcs.LG
Language models gain from varied answers, not necessarily altered weights
Output diversity, not weight-space experts, explains the gains from random perturbations in pretrained models.
Kyutai, Meta FAIR · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.