Hyperbolic Inverse Reinforcement Learning
Hyperbolic distance parameterization of rewards boosts IRL accuracy in low-data regimes and reveals non-separable conjunctive structures.
Stories per day · 30 days
1 RSS
Relatedalignment2agentic-distillation1differential-privacy1healthbench1hyperbolic-embedding1inverse-reinforcement-learning1llm-agents1llm-evaluation1on-policy-distillation1preference-feedback1prompt-injection1qwen1rl-benchmarks1rlhf1rubrics1teacher-student1
10 stories, newest first · one card per story
Stories tagged #reward-modeling
Rubricon generates LLM rubrics without human preference labels
Rubric scores align 9% more with expert rubrics than the best compared synthetic method, and lift Qwen3.5-9B on HealthBench.
Paper bounds private sparse reward estimation from preference feedback
Sample-DP and Label-DP rates depend on sparse features s* rather than full model size d.
Reward-free repair targets myopic scoring in agentic distillation
R2S beat three agentic on-policy methods in all 12 teacher-student-environment cells, by 12.8 success points on average.
EDIC scores each external instruction before an LLM complies
On Qwen3-4B, the paper reports up to 7.7% better harmful rejection and 12.5% higher Arena-Hard-Auto utility.
Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
LatentGRM judges preferences in compressed latent space, cutting 8B judge time about 6–7x while matching SFT accuracy.
LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
LoGo combines global and spatially localized rewards to fix 3D inconsistency in camera-controlled long-horizon video generation across three base models.
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
MetaRubric fixes 'Vacuous Credit' in rubric-based RL using counterfactual prompts and evidence-aware scoring, lifting PubMedQA up to 20.4 points.
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
LexReward defines taxonomy-driven rewards over Style, Element, and Chain dimensions for legal LLMs, feeding DPO and per-dimension reward models for RL.
What Is RLCD? The Secret Behind Jev
A blog explains Jev's RLCD as calibrated multiway Plackett-Luce preference modeling rather than scalar rewards.
7