VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
hub
Generative reward models
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
RMGAP benchmark shows state-of-the-art reward models reach at most 49.27% Best-of-N accuracy when forced to select responses matching diverse preferences.
GenAC introduces generative critics with chain-of-thought reasoning and in-context conditioning to improve value approximation and downstream RL performance in LLMs compared to value-based and value-free baselines.
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
RUBRIC-ARROW is an alternating rubric generator and judge framework that uses probability-based scoring and pairwise preferences to improve pointwise reward modeling accuracy for LLM post-training in non-verifiable domains.
RationalRewards recovers rationales from preference data via PARROT to create a critique-first reward model that improves visual generators at both training time through RL and test time through prompt refinement, matching RL fine-tuning performance while using far less data.
MISE proves that hindsight self-evaluation rewards equal minimizing mutual information plus KL divergence to a proxy policy, and experiments show 7B LLMs reaching GPT-4o-level results on validation tasks.
ReflectRM improves generative reward models by adding self-reflection on analysis quality within a unified training setup for response and analysis preferences, yielding accuracy gains and reduced positional bias on benchmarks.
UniCreative uses reference-free RL with an adaptive constraint-aware reward model to unify long-form coherence and short-form creativity in AI writing, producing an emergent ability to switch between planning and direct generation.
PaTaRM converts pairwise preference data into pointwise reward signals via a novel PAR mechanism and task-adaptive rubrics, reporting 8.7% gains on RewardBench/RMBench and 13.6% relative RLHF improvement.
GSR jointly trains LLMs to generate candidate solutions and refine a superior final answer from them, achieving state-of-the-art performance on five mathematical benchmarks while transferring across model scales.
RewardBench 2 is a new benchmark that supplies challenging fresh human prompts for reward model evaluation, yielding lower average scores but higher correlation with downstream best-of-N sampling and RLHF training performance.
REAR decomposes the reward into question and preference components, rescales their balance, and expresses the result as a linear combination of token log-probabilities for efficient integration with best-of-N and tree search.
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
CARE-RL combines PA-GRM for task-adaptive rewards on open-ended tasks and DACSP for modulating RL updates using historical capability directions, reporting higher total average scores than baselines on Qwen models.
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.
ConsistRM improves generative reward models via consistency-aware self-training, outperforming vanilla RFT by 1.5% on average across five benchmarks and four base models.
GenCluster scales test-time compute via large-scale generation, behavioral clustering, ranking, and round-robin submission to achieve IOI gold medal performance with the open-weight gpt-oss-120b model.
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
citing papers explorer
-
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
-
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
GSR jointly trains LLMs to generate candidate solutions and refine a superior final answer from them, achieving state-of-the-art performance on five mathematical benchmarks while transferring across model scales.