When Can LLMs Learn to Reason with Weak Supervision?

↘ Related papers

• Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
  Justin Bauer62% match
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
  Zhenwen Liang60% match
• GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
  Alireza Dadgarnia40% match
• Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
  A. Sophia Koepke38% match
• Using large language models for embodied planning introduces systematic safety risks
  Tao Zhang37% match