Presents a likelihood-based benchmark for equation-suffix prediction in technical papers with controls to detect shortcut vulnerabilities in model forecasts.
Likelihood- based reward designs for general llm reasoning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
SR-PPO trains a Pass@k critic from single-rollout Monte Carlo outcomes to enable token-level advantage estimation in language model RL, yielding stable training and Pass@128 gains on math benchmarks.
G-Zero uses the Hint-δ intrinsic reward to drive co-evolution between a Proposer and Generator via GRPO and DPO, providing a theoretical suboptimality guarantee for self-improvement from internal dynamics alone.
A new pipeline uses interpretability to characterize concepts in preference data and shape rewards via feature or data interventions during LM post-training.
citing papers explorer
-
Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities
Presents a likelihood-based benchmark for equation-suffix prediction in technical papers with controls to detect shortcut vulnerabilities in model forecasts.
-
Learning with a Single Rollout via Monte Carlo Pass@k Critic
SR-PPO trains a Pass@k critic from single-rollout Monte Carlo outcomes to enable token-level advantage estimation in language model RL, yielding stable training and Pass@128 gains on math benchmarks.
-
G-Zero: Self-Play for Open-Ended Generation from Zero Data
G-Zero uses the Hint-δ intrinsic reward to drive co-evolution between a Proposer and Generator via GRPO and DPO, providing a theoretical suboptimality guarantee for self-improvement from internal dynamics alone.
-
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
A new pipeline uses interpretability to characterize concepts in preference data and shape rewards via feature or data interventions during LM post-training.