Vision Paper: Why Distributed LLM Post-Training and Decentralized Alignment Are Now Essential
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- ORPO: Monolithic Preference Optimization without Reference Model
- Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy
- A Survey on Federated Fine-tuning of Large Language Models
- Anisotropic $(p,q)$-equations with convex and negative concave terms
- Federated Large Language Models: Current Progress and Future Directions
- FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment
- POPri: Private Federated Learning using Preference-Optimized Synthetic Data
- DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison
- UltraFeedback: Boosting Language Models with Scaled AI Feedback
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents