Gradient-Aligned Pair Selection for Personalized Preference Optimization
cs.AI
Submitted: 2026-09-04
Updated: 2026-09-04
Sources
- LoRe: Personalizing LLMs via Low-Rank Reward Modeling
- Personalized LLM Decoding via Contrasting Personal Preference
- Bootstrapping Language Models with DPO Implicit Rewards
- LLM Agents for Education: Advances and Applications
- KTO: Model Alignment as Prospect Theoretic Optimization
- From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
- ORPO: Monolithic Preference Optimization without Reference Model
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- Unsupervised Dense Information Retrieval with Contrastive Learning
- Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- Gradient Imbalance in Direct Preference Optimization
- Learning to summarize user information for personalized reinforcement learning from human feedback
- Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
- Proximal Policy Optimization Algorithms
- P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist
- Language Model Personalization via Reward Factorization
- PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data
- Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts
- Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems