LLM Alignment

LLM: Large Language Model

Overview

LLM alignment studies how to shape language models’ behavior so they are helpful, truthful, safe, and responsive to the people and settings they serve. Common approaches include supervised fine-tuning, preference learning such as Direct Preference Optimization, reinforcement learning from human or AI feedback, and inference-time steering or retrieval. Researchers evaluate these methods on instruction-following, preference, jailbreak, factuality, multilingual, and multi-turn tasks, while also developing ways to represent disagreement among users and communities. A central challenge is that gains in safety or preference alignment may reduce usefulness, diversity, calibration, or capability, and desired behavior may not generalize to new prompts, groups, or deployment settings.

Latest papers

CardsList

634 papers24 papers in the last four weeks, down 64% on the four weeks before. 0.2% of all new papers.

  1. Can you make models believe false facts in the prompt?

    Nov 18, 2026Ananya Sutradhar, Fabien RogerFine-TuningBelief Updating in LLMs

  2. Margin Dynamics for Large Language Model Alignment

    Nov 16, 2026Xingzi Xu, Mehmet Saygin Seyfioglu, Karim BouyarmaneLLM AlignmentPreference Learning for LLMs

  3. Enforcing Axioms for AI Alignment under Loss-Based Rules

    Nov 9, 2026Alexandros Hollender, Sonja KraiczyLLM AlignmentReward Modeling

  4. PORT: Preference Optimization via Robust Token-Level Reweighting

    Nov 9, 2026Ding Zhu, Xiukun Wei, Tian Xie +3Preference Learning for LLMsLLM Alignment

  5. Proximal Preference Optimization: A Unified Framework for Stable and Reward-Free Alignment

    Nov 7, 2026Qisai Liu, Zhanhong Jiang, Zahid Hasan +1LLM AlignmentPreference Optimization

  6. AERO: Adaptive Ensemble-Disagreement Routing for Oracle Feedback in Sample-Efficient Online RLHF

    Nov 7, 2026Shrey Singhal, Nannan Huang, Haytham M. FayekLLM AlignmentRL from Human Feedback

  7. SAVeR2^2: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards

    Nov 5, 2026Yichen Sun, Qirui Liu, Yan Wang +5LLM Safety AlignmentSafety-Preserving Fine-Tuning of Language Models

  8. Objective-Conditioned Active Preference Learning for Multi-Objective Alignment

    Nov 3, 2026Duc Anh Vu, Thong Nguyen, Hoang Pham +2LLM AlignmentMulti-Objective Language Model Alignment

  9. Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization

    Nov 3, 2026Austin Tsai, Saurav Nanda, Ganapathy Parthasarathy +2LLM AlignmentPreference Optimization

  10. Suppressing Misaligned Behaviors in Language Models, Durably

    Nov 3, 2026Luxi He, Pengcheng Jiang, Jifan Zhang +2LLM AlignmentLLM Unlearning

  11. Measuring Model-Specific Alignment Drift in LLM-Based Opinion Dynamics

    Nov 2, 2026Nataša Djurdjevac Conrad, Sebastian Pokutta, Christof SchütteLarge Language Model-Based Social SimulationBehavioral Consistency of LLM Agents

  12. VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations

    Nov 2, 2026Avni Mittal, Avinash Anand, Dikshant Kukreja +3LLM AlignmentLanguage Model Steering

  13. Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions

    Oct 30, 2026Ning E, Changde Du, Yizhuo Lu +1LLM AlignmentMultimodal Large Language Models

  14. Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning

    Oct 30, 2026Bin Luo, Param Venkat Vivek Kesireddy, Anil VallepuDirect Preference OptimizationPreference Learning

  15. Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions

    Oct 27, 2026Chen Lyu, Phong Do, Gabriele PergolaLLM AlignmentLLM-as-a-Judge

  16. On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime

    Oct 27, 2026Kensuke Sasaki, Issei SatoDirect Preference OptimizationLLM Alignment

  17. Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization

    Oct 27, 2026Giuseppe Curci, Stefano Simonazzi, Andrea Molinari +1Direct Preference OptimizationLLM Alignment

  18. AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases

    Oct 23, 2026Yi Qi, Srijoni Majumdar, Evangelos PournarasDemographic Bias in Language ModelsLLM Alignment

  19. Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design

    Oct 22, 2026Siliang Zeng, Luca Viano, Chenliang Li +6LLM AlignmentRL from Human Feedback

  20. Unintended Side Effects of Value Training in LLMs

    Oct 21, 2026Siddhesh Pawar, Chen Cecilia Liu, Anna Korhonen +1LLM AlignmentLanguage Model Post-Training

  21. LaVGuard: Selective Decoding for Contextual Value Drift

    Oct 21, 2026Jiale Dai, Liuxian Ma, Hongcan Deng +5LLM AlignmentLanguage Model Decoding

  22. TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization

    Oct 20, 2026Chengtao Jian, Kai YangLLM AlignmentDirect Preference Optimization

  23. CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition

    Oct 20, 2026Sasi Kiran Gaddipati, Gollam Rabby, Sören AuerLLM AlignmentReward Modeling

  24. Divergence based Ranked Preference Alignment for LLMs

    Oct 18, 2026Rajdeep Haldar, Yue Xing, Qifan SongLLM AlignmentPreference Alignment

  25. When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice

    Oct 18, 2026Dean Ariel, Guy LabanLLM EvaluationLanguage Model Generation Evaluation

  26. Aligning Cultural Behaviors in Arabic Language Models via Preferences

    Oct 18, 2026Junhong Liang, Daniil Orel, Saeed Almheiri +11Arabic Language ModelsCultural Alignment