Uniform Information Density-Based Preference Optimization
cs.CL
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/CLCS-SUSTech/UIDPO
Sources
- A General Language Assistant as a Laboratory for Alignment
- A General Theoretical Paradigm to Understand Learning from Human Preferences
- Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- UltraFeedback: Boosting Language Models with Scaled AI Feedback
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- KTO: Model Alignment as Prospect Theoretic Optimization
- Revisiting the Uniform Information Density Hypothesis in LLM Reasoning
- Mistral 7B
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- SimPO: Simple Preference Optimization with a Reference-Free Reward
- Identifying the Periodicity of Information in Natural Language
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Proximal Policy Optimization Algorithms
- Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
- Constrain Alignment with Sparse Autoencoders
- SLiC-HF: Sequence Likelihood Calibration with Human Feedback
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering