Showing 1–11 of 11 results
/ Date/ Name
Apr 18, 2021Flexible Generation of Natural Language DeductionsJan 16, 2022Natural Language Deduction through Search over Statement CompositionsApr 7, 2020Byte Pair Encoding is Suboptimal for Language Model PretrainingJul 5, 2023Deductive Additivity for Planning of Natural Language ProofsFeb 6, 2026Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward ModelingJan 9, 2026MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code OptimizationOct 24, 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft ReasoningNov 1, 2022Natural Language Deduction with Incomplete InformationNov 6, 2025VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency ChecksFeb 23, 2026ReSyn: Autonomously Scaling Synthetic Environments for Reasoning ModelsOct 26, 2023Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways