LLM Alignment

LLM: Large Language Model

Ask about this topic

Momentum

48 papers in the last four weeks, up 118% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 422

All topics
CardsList

  1. The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

    Jun 17, 2026Naihao Deng, Yiming Feng, Chimaobi Okite +4LLM GroundingLLM Alignment

    University of Michigan · University of Cambridge · University of Aberdeen

  2. SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data

    Jun 15, 2026Wenjie Wang, Yue Huang, Zhengqing Yuan +6LLM AlignmentSynthetic Data Generation

    University of Notre Dame · Carnegie Mellon University · LMU Munich +1

  3. Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

    Jun 13, 2026Ali Dasdan, Manan Shah, W. Russell Neuman +3LLM AlignmentMoral Reasoning in Language Models

    1KD Consulting, CA, USA · 2New York University, NY, USA

  4. Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment

    Jun 12, 2026Jihye Kim, Jeffrey FlaniganLLM AlignmentMoral Reasoning in Language Models

    University of California, Santa Cruz

  5. Evaluating Pluralism in LLMs through Latent Perspectives

    Jun 11, 2026Laura Majer, Jan Šnajder, Martin TutekLLM EvaluationLLM Alignment

    TakeLab, University of Zagreb, Croatia.

  6. PolyAlign: Conditional Human-Distribution Alignment

    Jun 11, 2026L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2Multilingual Language ModelsLLM Alignment

    NIT Silchar, India · MBZUAI, Abu Dhabi, UAE

  7. Understanding helpfulness and harmless tension in reward models

    Jun 11, 2026Eshaan Tanwar, Pepa AtanasovaReward ModelingLLM Alignment

    University of Copenhagen

  8. Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study

    Jun 11, 2026Dezhi Yu, Yvonne Qiu, ShuoJia FuLLM AlignmentDirect Preference Optimization

  9. LLMs Can Better Capture Human Judgments--With the Right Prompts

    Jun 10, 2026Danica Dillion, Chen Cecilia Liu, Baihui Wang +5Human Preference EvaluationLLM Alignment

    Complexity Science Hub, Vienna · The Ohio State University · University of Cambridge +2

  10. Boosting Direct Preference Optimization with Penalization

    Jun 10, 2026Pengwei SunPairwise Preference LearningLLM Alignment

    Stanford University.

  11. ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

    Jun 10, 2026Chirag Chawla, Pratinav Seth, Vinay Kumar SankarapuLLM AlignmentLLM Safety Alignment

    Lexsi Labs

  12. Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

    Jun 9, 2026Malikeh Ehghaghi, Boglárka Ecsedi, Marsha Chechik +1LLM AlignmentNeural Network Robustness

    University of Toronto · Vector Institute · Hugging Face

  13. Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models

    Jun 9, 2026Prajakta Kini, Avinash Reddy, Souradip Chakraborty +4LLM AlignmentLanguage Model Safety Evaluation

    University of Colorado Boulder · University of Central Florida · University of Maryland College Park +1

  14. It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO

    Jun 9, 2026Naihao Deng, Yilun Zhu, Naichen Shi +2LLM AlignmentSocial Bias in Language Models

    University of Michigan · Northwestern University

  15. When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

    Jun 9, 2026Sai Kartheek Reddy Kasu, Nils Lukas, Samuele PoppiCoT FaithfulnessLLM Alignment

    Independent Researcher · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)

  16. Alignment Defends LLMs from Property Inference Attacks

    Jun 8, 2026Pengrun Huang, Chhavi Yadav, Ruihan Wu +1LLM AlignmentPrivacy Leakage in Language Models

    University of California, San Diego · Carnegie Mellon University · Simons Institute, UC Berkeley

  17. The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

    Jun 8, 2026Wendy K. TamLLM AlignmentLLM Interpretability

    Professor and Stevenson Chair in the Departments of Political Science, Computer Science, Biomedical Informatics, and the Law School at Vanderbilt University, and an affiliate of the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign

  18. Gradient-Guided Reward Optimization for Inference-time Alignment

    Jun 8, 2026Hankun Lin, Ruqi ZhangReward HackingLLM Alignment

    Department of Computer Science, Purdue University

  19. A Regret Minimization Framework on Preference Learning in Large Language Models

    Jun 8, 2026Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim +4Regret Minimization in RLLLM Alignment

    Seoul National University, Seoul, South Korea · LG AI Research, Seoul, South Korea · UNIST, Ulsan, South Korea +1

  20. Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

    Jun 8, 2026Sicheng Wang, Xiangyang Zhu, Han Wang +6LLM SycophancyLLM Alignment

    Shanghai AI Lab, Shanghai, China.

  21. Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning

    Jun 8, 2026Trapoom Ukarapol, Pakhapoom Sarapat, Nut ChukamphaengMultilingual Language ModelsLLM Alignment

    §SCB DataX · ‡Tsinghua University · †SCBX

  22. Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

    Jun 8, 2026Mikhail Krasitskii, Alexander Gelbukh, Olga Kolesnikova +1LLM AlignmentText Summarization

    Instituto Politécnico Nacional (IPN), Centro de Investigación en Computación (CIC), Mexico City, Mexico

  23. Sycophancy Towards Researchers Drives Performative Misalignment

    Jun 7, 2026David D. Baek, Xinnuo Li, Anay Gupta +4LLM SycophancyLLM Alignment

    Massachusetts Institute of Technology, Cambridge, MA, USA · University of Michigan, Ann Arbor, MI, USA · Georgia Institute of Technology, Atlanta, GA, USA +1

  24. Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models

    Jun 7, 2026Arya Shah, Himanshu Beniwal, Mayank Singh +1Multilingual Language ModelsMultilingual Language Model Evaluation

    IIT Gandhinagar · Asian Institute of Technology

  25. Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard

    Jun 7, 2026Alireza Arbabi, Florian KerschbaumLLM AlignmentLLM Auditing

    Department of Computer Science, University of Waterloo, Waterloo, ON, Canada · Vector Institute, Toronto, ON, Canada

  26. LCAM: A Framework for Diagnosing Interactional Alignment Failures in Con-versational AI

    Jun 6, 2026Manuele Reani, Hongyu TianLLM AlignmentLLM Safety Alignment

    School of Management and Economics, The Chinese University of Hong Kong, Shenzhen, China

  27. PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

    Jun 6, 2026Xiaoyan Zhao, Haoting Ni, Yang Zhang +3Reward ModelingLLM Alignment

    National University of Singapore · University of Science and Technology of China · Peking University

  28. Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks

    Jun 6, 2026Haoming Wen, Shi Chen, Qingyu Shi +4Adversarial TrainingLLM Alignment

    1Xiongan AI Institute · Institute for Interdisciplinary Information Sciences, Tsinghua University · 3Shanghai Qi Zhi Institute

  29. Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models

    Jun 5, 2026Angana Borah, Isabelle Augenstein, Rada MihalceaLLM AlignmentNormative Conformity in Language Models

    University of Michigan - Ann Arbor · University of Copenhagen

  30. Sycophantic Praise: Evaluating Excessive Praise in Language Models

    Jun 5, 2026Daniel Vennemeyer, Phan Anh Duong, Meryl Ye +2LLM EvaluationLLM Sycophancy

    University of Cincinnati · Carnegie Mellon University · Texas A&M University