conftrace_

inference compute

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) sampling strategies (1) early rejection (1) win-rate evaluation (1) compute democratization (1) multilingual math (1) aggregate success trend (1) exponential failure rate (1) single-attempt success probability (1) power-law scaling (1)

Papers

Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling EMNLP 2025 How Do Large Language Monkeys Get Their Power (Laws)? ICML 2025 Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning ACL 2025 When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs EMNLP 2025