SVR learns a bank of contrastive rubrics from preference data via max-margin boundaries and prompt-conditioned selection, narrowing the gap to human rubrics on RubricBench from 24.1 to 0.3 points.
Rewardanything: Generalizable principle-following reward models
6 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1
external citations · external index
verdicts
UNVERDICTED 6representative citing papers
DoGMaTiQ automates creation of QA-based nuggets via document-grounded generation, paraphrase clustering, and quality subselection, producing report evaluations that correlate strongly with human judgments on cross-lingual TREC tasks.
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
Skill-RM unifies heterogeneous reward criteria by modeling reward computation as dynamic execution of a reusable Reward-Evaluation Skill within an agent framework.
RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
A reasoning-distillation plus dual-reward GRPO method for multi-role dialogue summarization matches ROUGE and BERTScore baselines while improving factual faithfulness and preference alignment on CSDS and SAMSum.
citing papers explorer
-
Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics
SVR learns a bank of contrastive rubrics from preference data via max-margin boundaries and prompt-conditioned selection, narrowing the gap to human rubrics on RubricBench from 24.1 to 0.3 points.
-
DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation
DoGMaTiQ automates creation of QA-based nuggets via document-grounded generation, paraphrase clustering, and quality subselection, producing report evaluations that correlate strongly with human judgments on cross-lingual TREC tasks.
-
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
A rubric-based generative reward model improves reinforced fine-tuning of SWE agents by supplying richer behavioral guidance than binary terminal rewards alone.
-
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Skill-RM unifies heterogeneous reward criteria by modeling reward computation as dynamic execution of a reusable Reward-Evaluation Skill within an agent framework.
-
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
-
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
A reasoning-distillation plus dual-reward GRPO method for multi-role dialogue summarization matches ROUGE and BERTScore baselines while improving factual faithfulness and preference alignment on CSDS and SAMSum.