Entities · Models
GSM8K
13 articles tagged with this entity.
-
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation
-
Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
-
Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization
-
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
-
Did You Forget What I Asked? Prospective Memory Failures in Large Language Models
-
The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning
-
Learning from Saturated Data: Signals Beyond Correctness for LLM Training
-
The Distillation Game: Adaptive Attacks & Efficient Defenses
-
The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic
-
BPPO: Binary Prefix Policy Optimization for Efficient GRPO-Style Reasoning RL with Concise Responses
-
GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations
-
Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
-
Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks