ReadHuman or Synthetic? What a Fixed Budget Buys for Post-Training#post-training#dpoarXiv: Machine LearningarticleNov 13, 2026
ReadHow Post-Training Influences Verbalized Algorithmic Computation in Language Models#post-training#llm-reasoningarXiv: Machine LearningarticleNov 11, 2026
ReadProximal Preference Optimization: A Unified Framework for Stable and Reward-Free Alignment#dpo#ai alignmentarXiv: Artificial IntelligencearticleNov 10, 2026
ReadDon't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training#post-training#LLM evaluation / benchmarkingarXiv: Artificial IntelligencearticleNov 10, 2026
ReadSeeing Isn't Enough: Unlocking Visual Reasoning by Bridging the Reasoning-Access Gap with TIGER#llm-reasoning#Artificial IntelligencearXiv: Artificial IntelligencearticleNov 10, 2026
ReadTLRS-DPO: Token-Level Risk Scoring for Better Direct Preference Optimization#dpoarXiv: Artificial IntelligencearticleNov 10, 2026
ReadPersonalized Alignment of Language Models with Human Value Profiles#ai alignment#personalizationarXiv: Artificial IntelligencearticleNov 10, 2026
ReadWhen Scores Conflict with Preferences: Pre-Alignment Diagnosis and Adaptive Correction of Constraint Drift in DPO#dpo#ai alignmentarXiv: Machine LearningnewsNov 6, 2026
ReadThe Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention#dpo#ai alignmentarXiv: Machine LearningarticleNov 6, 2026
ReadVision Paper: Why Distributed LLM Post-Training and Decentralized Alignment Are Now Essential#post-training#ai alignmentarXiv: Artificial IntelligenceopinionNov 5, 2026
ReadObjective-Conditioned Active Preference Learning for Multi-Objective Alignment#dpo#ai alignmentarXiv: Artificial IntelligencearticleNov 5, 2026
ReadAligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization#ai alignment#dpoarXiv: Artificial IntelligencearticleNov 4, 2026
ReadTopoDPO: Dense Preference Alignment for Structure-Sensitive Aerial Referring Segmentation#dpoarXiv: Artificial IntelligencearticleNov 3, 2026
ReadAxion 1.0: Open Agent Foundation Models, Simplified#AI Foundation Models#llm-reasoningarXiv: Artificial IntelligencereleaseNov 3, 2026
ReadPredicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings#ai alignment#human feedbackarXiv: Artificial IntelligencearticleNov 2, 2026
ReadReliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning#dpo#Fine-tuningarXiv: Machine LearningarticleNov 2, 2026
ReadSecPO: Principled Adversarial Training for Prompt Injection Security#prompt injection#LLM securityarXiv: Artificial IntelligencearticleNov 2, 2026
ReadThe Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology#LLM evaluation / benchmarking#post-trainingarXiv: Machine LearningarticleOct 30, 2026
ReadLearning Where It Matters: Geometric Anchoring for Robust Preference Alignment#dpo#ai alignmentarXiv: Machine LearningarticleOct 30, 2026
ReadExploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization#dpo#Machine learningarXiv: Artificial IntelligencenewsOct 28, 2026
ReadOn the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime#dpo#rlhfarXiv: Machine LearningarticleOct 28, 2026
ReadAligning Large Language Models for Safety in African Languages: A Case Study of Hausa#ai alignment#dpoarXiv: Artificial IntelligencearticleOct 28, 2026
ReadAligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design#ai alignment#rlhfarXiv: Machine LearningarticleOct 26, 2026