No article text was recorded for this version.
synthetic preference data generation
Version 1 of 1139 papers159 conceptsfrozen 2026-10-04
Papers in this version
- Blog: MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
- Blog: Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
- Blog: Configurable Preference Tuning with Rubric-Guided Synthetic Data
- Blog: Aligning Text-to-Image Diffusion Models to Human Preference by Classification
- Blog: Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization
- Blog: Zephyr: Direct Distillation of LM Alignment
- Blog: Value Alignment from Unstructured Text
- Blog: Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
- Blog: Scalable Ranked Preference Optimization for Text-to-Image Generation
- Blog: Self-Taught Evaluators
- Blog: Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
- Blog: Value Alignment from Unstructured Text
- Blog: PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
- Blog: From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
- Blog: RLVF: Learning from Verbal Feedback without Overgeneralization
- Blog: SpeechAlign: Aligning Speech Generation to Human Preferences
- Blog: Sequence-level Large Language Model Training with Contrastive Preference Optimization
- Blog: AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation
- Blog: Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation
- Blog: MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
- Blog: Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs
- Blog: Towards a Unified View of Preference Learning for Large Language Models: A Survey
- Blog: Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments
- Blog: Pedagogical Alignment of Large Language Models
- Blog: CodeArena: Evaluating and Aligning CodeLLMs on Human Preference
- Blog: Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
- Blog: Improving Large Vision and Language Models by Learning from a Panel of Peers
- Blog: Automatic Prompt Selection for Large Language Models
- Blog: Persona-Aware Alignment Framework for Personalized Dialogue Generation
- Blog: J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
- Blog: DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
- Blog: Discriminator-Free Direct Preference Optimization for Video Diffusion
- Blog: Self-rationalization improves LLM as a fine-grained judge
- Blog: Course-Correction: Safety Alignment Using Synthetic Preferences
- Blog: SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
- Blog: TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
- Blog: ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
- Blog: Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
- Blog: From Demonstrations to Rewards: Alignment Without Explicit Human Preferences
- Blog: Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
- Blog: PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs
- Blog: Chinchunmei at SemEval-2025 Task 11: Boosting the Large Language Model's Capability of Emotion Perception using Contrastive Learning
- Blog: Direct Preference Optimization for Speech Autoregressive Diffusion Models
- Blog: TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning
- Blog: The Paradox of Preference: A Study on LLM Alignment Algorithms and Data Acquisition Methods
- Blog: More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
- Blog: Language Models as Continuous Self-Evolving Data Engineers
- Blog: SALMON: Self-Alignment with Instructable Reward Models
- Blog: One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning
- Blog: Self-Supervised Visual Preference Alignment
- Blog: Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
- Blog: SPUR: Scaling Reward Learning from Human Demonstrations
- Blog: Federated Learning for Personalized Humor Recognition
- Blog: CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning
- Blog: Weaving in the Clouds: Achieving Synergistic Collaboration among LLM Agents via Federated Learning
- Blog: MuCAL: Contrastive Alignment for Preference-Driven KG-to-Text Generation
- Blog: Alignment-Aware Decoding
- Blog: Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
- Blog: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
- Blog: Improving Alignment in LVLMs with Debiased Self-Judgment
Showing 60 of 139 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_synthetic_preference_data_generation_d5b3ef50,
title = {synthetic preference data generation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-preference-data-generation/rdr_d5b3ef50883542b1ab5f3687ce267bb6},
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_synthetic_preference_data_generation_d5b3ef50_v1,
title = {synthetic preference data generation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-preference-data-generation/rdr_d5b3ef50883542b1ab5f3687ce267bb6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}