Cites: Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

4 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• The Llama 3 Herd of Models
  arxiv:2407.21783 · evidence: id
• 2 OLMo 2 Furious
  arxiv:2501.00656 · evidence: id
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  arxiv:2504.13837 · evidence: id
• Spurious Rewards: Rethinking Training Signals in RLVR
  arxiv:2506.10947 · evidence: id