RGSD distills rubric-conditioned teacher distributions into base policies token-by-token, matching GRPO rubric satisfaction on Qwen models with one rollout and zero verifier calls.
Does this image satisfy this rule?
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
method 1polarities
use method 1representative citing papers
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
ARL-RR alternates optimization over rubric meta-classes with dynamic selection to avoid fixed scalarization, outperforming baselines on HealthBench.
DR-rubric is a two-stage framework using iterative agentic search to generate atomic verifiable constraints for GRPO-based RL, achieving competitive performance on 6 benchmarks with 1K-3K examples via bootstrap or frontier-model rubrics.
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
A new pipeline uses interpretability to characterize concepts in preference data and shape rewards via feature or data interventions during LM post-training.
QUBRIC co-designs queries and rubrics via teacher key points, contrastive generation, and learnability filtering to support GRPO training, yielding +5.5 on ArenaHard and +6.3 average transfer to legal/moral/narrative benchmarks.
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.
citing papers explorer
No citing papers match the current filters.