LLM Alignment

LLM: Large Language Model

Ask about this topic

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

613 papers58 papers in the last four weeks, up 12% on the four weeks before. 0.3% of all new papers.

  1. Backdoor Attacks on Decentralised Post-Training

    Mar 31, 2026Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3LLM Backdoor AttacksLanguage Model Post-Training

    Gensyn · University of Neuchâtel · Radboud University +3

  2. Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models

    Mar 31, 2026Christine Zhang, Dan Jurafsky, Chen ShaniLanguage ModelingLLM Alignment

    Stanford University

  3. Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study of 5W3H Prompting

    Mar 26, 2026Peng GangStructured PromptingLLM Prompting

    Huizhou Lateni AI Technology Co., Ltd., Huizhou, China · Huizhou University, Huizhou, China

  4. Correcting Suppressed Log-Probabilities in Language Models with Post-Transformer Adapters

    Mar 25, 2026Bryan SanchezLLM AlignmentPolitical Bias in Language Models

  5. Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study

    Mar 25, 2026Nour Bouchouchi, Thibault Laugel, Xavier Renard +3Gender Bias in Language ModelsLLM Alignment

    Sorbonne Université, CNRS, LIP6, F-75005 Paris, France · AXA, Paris, France · Polish Academy of Science, IBS PAN, Warsaw, Poland

  6. The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation

    Mar 25, 2026Mingyi LiuHomogenization in Language ModelsLLM Alignment

    Independent Researcher

  7. Unbiased Reward Modeling from Implicit Feedback for LLM Alignment

    Mar 24, 2026Hao Wang, Haocheng Yang, Licheng Pan +7Reward ModelingLLM Alignment

    Peking University · Xiaohongshu Inc. · National University of Singapore +1

  8. When Language Models Lose Their Mind: The Consequences of Brain Misalignment

    Mar 24, 2026Gabriele Merlin, Mariya TonevaLLM Alignment

    MPI-SWS, Saarbrücken, Germany

  9. Improving Safety Alignment via Balanced Direct Preference Optimization

    Mar 24, 2026Shiji Zhao, Mengyang Wang, Shukun Xiong +7LLM Safety AlignmentLLM Alignment

    Institute of Artificial Intelligence, Beihang University, Beijing, China.

  10. Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models

    Mar 23, 2026Aryan Kasat, Smriti Singh, Aman Chadha +1Moral Reasoning in Language ModelsReasoning Consistency in Language Models

    UT Austin · Google GenAI

  11. Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

    Mar 21, 2026Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1LLM AlignmentMemorization in Language Models

    Stony Brook University · Carnegie Mellon University · Columbia Law School

  12. Alignment midtraining for animals

    Mar 21, 2026Jasmine Brazilek, Miles TidmarshLLM AlignmentLLM Training

    Compassion Aligned Machine Learning

  13. Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

    Mar 19, 2026Matt Gorbett, Suman JanaLatent Space AlignmentLLM Alignment

    Capital One New York, NY 10003, USA · Department of Computer Science Columbia University New York, NY 10027, USA

  14. Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions

    Mar 19, 2026Xiaoyi LiLanguage Model Post-TrainingLLM Alignment

  15. Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization

    Mar 18, 2026Haocheng Luo, Zehang Deng, Thanh-Toan Do +3LLM AlignmentDirect Preference Optimization

    Monash University, Australia · Swinburne University of Technology, Australia

  16. VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models

    Mar 18, 2026Hefei Xu, Le Wu, Yu Wang +4LLM AlignmentMulti-Objective Language Model Alignment

    Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei, Anhui, China · Innovation School of Artificial Intelligence, Hefei University of Technology

  17. Alignment Makes Language Models Normative, Not Descriptive

    Mar 17, 2026Eilam Shapira, Moshe Tennenholtz, Roi ReichartLLM AlignmentPreference Alignment

    Technion – Israel Institute of Technology

  18. Prompt Programming for Cultural Bias and Alignment of Large Language Models

    Mar 17, 2026Maksim Eren, Eric Michalak, Brian Cook +1LLM AlignmentCultural Alignment

    Advanced Research in Cyber Systems, Los Alamos National Laboratory, Los Alamos, New Mexico, USA · Analytics Division, Los Alamos National Laboratory, Los Alamos, New Mexico, USA

  19. Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model

    Mar 17, 2026Ryo Kishino, Riku Shiomi, Hiroaki Yamagiwa +2Language Model PretrainingLLM Alignment

    1Kyoto University · 2RIKEN

  20. Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences

    Mar 17, 2026Quan ChengLLM AlignmentRL from Human Feedback

    Tsinghua University

  21. PlotTwist: A Creative Plot Generation Framework with Small Language Models

    Mar 17, 2026Abhinav Thorat, Ravi Kolla, Jyotin Goel +2Narrative GenerationSmall Language Models

    Sony Research India

  22. HIPO: Instruction Hierarchy via Constrained Reinforcement Learning

    Mar 17, 2026Keru Chen, Jun Luo, Sen Lin +4LLM AlignmentRL for Language Models

    School of ECEE Arizona State University · Department of ECE The Ohio State University · Computer Science Department University of Houston +2

  23. Mechanistic Origin of Moral Indifference in Language Models

    Mar 16, 2026Lingyu Li, Yan Teng, Yingchun WangLLM AlignmentMoral Reasoning in Language Models

    Shanghai Artificial Intelligence Laboratory

  24. Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph

    Mar 16, 2026Zhenheng Tang, Xiang Liu, Qian Wang +3LLM AlignmentLLM Safety

    The Hong Kong University of Science and Technology · The Hong Kong University of Science and Technology (Guangzhou) · New York University +1

  25. Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

    Mar 16, 2026Jaehyeok Lee, Xiaoyuan Yi, Jing Yao +4LLM EvaluationLLM Alignment

    Sungkyunkwan University · Microsoft Research Asia · Singapore University of Technology and Design

  26. Beyond Creed: A Non-Identity Safety Condition A Strong Empirical Alternative to Identity Framing in Low-Data LoRA Fine-Tuning

    Mar 16, 2026Xinran ZhangSafety-Preserving Fine-Tuning of Language ModelsLLM Safety

    University of California, Berkeley

  27. PA3: Policy-Aware Agent Alignment through Chain-of-Thought

    Mar 15, 2026Shubhashis Roy Dipta, Daniel Bis, Kun Zhou +4LLM AlignmentRL for Language Model Reasoning

    University of Maryland, Baltimore County · Amazon Alexa AI

  28. An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs

    Mar 15, 2026Qian Zhu, Xinnan Guo, Jingjing Huo +5Domain Adaptation for LLMsLLM Alignment

    Ant Group

  29. Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion

    Mar 14, 2026Minghan Li, Guodong ZhouLanguage Model DistillationEfficient Language Model Inference

    School of Computer Science and Technology, Soochow University, China

  30. CLARIN-PT-LDB: An Open LLM Leaderboard for Portuguese to assess Language, Culture and Civility

    Mar 13, 2026João Silva, Luís Gomes, António BrancoLLM EvaluationPortuguese Language Models

    University of Lisbon NLX—Grupo de Fala e Linguagem Natural, Departmento de Informática Faculdade de Ciências, Campo Grande, 1749-016 Lisboa, Portugal