No article text was recorded for this version.
preference data scarcity
Version 1 of 185 papers87 conceptsfrozen 2026-10-04
Papers in this version
- Blog: RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
- Blog: Weak Human Preference Supervision for Deep Reinforcement Learning
- Blog: Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
- Blog: PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
- Blog: Scaling Reward Modeling without Human Supervision
- Blog: Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
- Blog: ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
- Blog: Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design
- Blog: SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning
- Blog: References Improve LLM Alignment in Non-Verifiable Domains
- Blog: Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model
- Blog: Semi-Supervised Reward Modeling via Iterative Self-Training
- Blog: BATON: Aligning Text-to-Audio Model Using Human Preference Feedback
- Blog: NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning
- Blog: Improving Reward Models with Synthetic Critiques
- Blog: Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models
- Blog: Batch Reinforcement Learning from Crowds
- Blog: Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
- Blog: PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers
- Blog: SALMON: Self-Alignment with Instructable Reward Models
- Blog: Online Knowledge Distillation with Reward Guidance
- Blog: Auto-Rubric: Learning to Extract Generalizable Criteria for Reward Modeling
- Blog: YaART: Yet Another ART Rendering Technology
- Blog: Prototypical Reward Network for Data-Efficient RLHF
- Blog: Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
- Blog: PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
- Blog: PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
- Blog: Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills
- Blog: PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
- Blog: Boosting Text-to-Video Generative Model with MLLMs Feedback
- Blog: Improving Reward Models with Synthetic Critiques
- Blog: Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
- Blog: Beyond Imitation: Recovering Dense Rewards from Demonstrations
- Blog: EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
- Blog: FSPO: Few-Shot Optimization of Synthetic Preferences Effectively Personalizes to Real Users
- Blog: Pre-Trained Policy Discriminators are General Reward Models
- Blog: Batch Policy Gradient Methods for Improving Neural Conversation Models
- Blog: PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
- Blog: PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
- Blog: Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation
- Blog: FashionDPO: Fine-tune Fashion Outfit Generation Model using Direct Preference Optimization
- Blog: CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning
- Blog: Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
- Blog: MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences
- Blog: MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization
- Blog: VLP: Vision-Language Preference Learning for Embodied Manipulation
- Blog: Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
- Blog: ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
- Blog: Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
- Blog: Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
- Blog: LLaVA-Critic: Learning to Evaluate Multimodal Models
- Blog: Cognitive Models as Simulators: The Case of Moral Decision-Making
- Blog: BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
- Blog: Efficient Exploration for LLMs
- Blog: Efficiently Acquiring Human Feedback with Bayesian Deep Learning
- Blog: BLEUBERI: BLEU is a surprisingly effective reward for instruction following
- Blog: Optimizing Reasoning for Text-to-SQL with Execution Feedback
- Blog: SELF-EVOLVED REWARD LEARNING FOR LLMS
- Blog: Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
- Blog: Aligning Language Models Using Follow-up Likelihood as Reward Signal
Showing 60 of 85 papers.
History & citation
Current · Permanent link
- This direction split from Scaling Model Alignment with Synthetic Preference Signals (68% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_preference_data_scarcity_e13bb001,
title = {preference data scarcity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/preference-data-scarcity/rdr_e13bb001970f48cd8a3f5dc339c60e7e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_preference_data_scarcity_e13bb001_v1,
title = {preference data scarcity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/preference-data-scarcity/rdr_e13bb001970f48cd8a3f5dc339c60e7e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}