Large Language Model Alignment

Ask about this topic

Momentum

37 papers in the last four weeks, up 118% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 295

All topics
CardsList

  1. Reward Stealing Attack on Large Language Models

    Oct 5, 2026Jiaming Qian, Pengyang Zhou, Jiahe Xu +1Attacker Large Language ModelLarge Language Model Reinforcement Learning

    Zhejiang University

  2. Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning

    Oct 1, 2026Zichen Xie, Mrigank Pawagi, Lize Shao +2Large Language Model Alignment

    University of Virginia · University of Pennsylvania · The University of Texas at Austin

  3. The Asymptotics of Language Model Alignment with Memory

    Oct 1, 2026Haricharan Balasundaram, V. Arvind RameshwarLarge Language Model AlignmentLanguage Modeling

    School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA · IIT Madras · Department of Electrical Engineering, IIT Madras, Chennai, India

  4. Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models

    Oct 1, 2026Tido Specht, Elias Benedict Krey, Nils Neukirch +1Large Language Model AlignmentMultimodal Large Language Models

    University of Groningen · Carl von Ossietzky University of Oldenburg

  5. HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix

    Oct 1, 2026Zirui He, Haiyan Zhao, Jingyu Hu +5Large Language Model AlignmentTuning

    New Jersey Institute of Technology · University of Bristol · Kuaishou Technology +1

  6. Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness

    Sep 30, 2026Pardis Sadat Zahraei, Janvijay Singh, Gokhan Tur +1Large Language Model AlignmentFaithfulness

    University of Illinois Urbana-Champaign

  7. Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering

    Sep 30, 2026Jiale Dai, Hongcan Deng, Liuxian Ma +2Large Language Model AlignmentEdit

    State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · University of Chinese Academy of Sciences · College of Artificial Intelligence, Tsinghua University

  8. Multi-LLM Collaborative Alignment via Stackelberg Games

    Sep 30, 2026Christina Hahn, Shangbin Feng, Dean Light +3Large Language Model AlignmentStackelberg Equilibrium

    University of Washington · Amazon · University of British Columbia

  9. LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection

    Sep 30, 2026Jahyeob Koo, Kio Yun, Byoungmo Koo +1Time-Series Anomaly DetectionTime Series

    Department of Industrial and Management Engineering, Korea University Seoul, Republic of Korea

  10. Aligned Data Can Induce Misalignment via Context Confusion

    Sep 29, 2026Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin +4Large Language Model AlignmentTraining-Inference Mismatch

    University of Southern California · Carnegie Mellon University · Amazon +1

  11. The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment

    Sep 29, 2026Gonçalo Paulo, Louis Jaburi, Nora Belrose +2Emergent MisalignmentLarge Language Model Alignment

    EleutherAI

  12. ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs

    Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Multilingual SafetyLarge Language Model Safety

    Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China

  13. Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

    Sep 28, 2026Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan +2Safety AlignmentLarge Reasoning Models

    Wayne State University

  14. Population Fidelity: Evaluating Population Representativeness in LLMs

    Sep 28, 2026Neemias B. da Silva, Martin Lukk, Ali Sutani +5Large Language Model BiasDemographics

    University of Toronto, Canada · Federal University of Technology – Paran´a, Brazil

  15. Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

    Sep 28, 2026Shunchang Liu, Lukas Fluri, Xin Chen +1Emergent MisalignmentModality Alignment

    ETH Zürich · EPFL · Aalto University +1

  16. From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data

    Sep 28, 2026Husrev Taha Sencar, Rezart Beka, Danish Naeem +6Large Language Model AlignmentSocial Norms

    Qatar Computing Research Institute, HBKU, Qatar. · College of Islamic Studies, HBKU, Qatar. · Argumentation and Conflict Studies, Ibn Haldun University, Turkiye. +1

  17. BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment

    Sep 28, 2026Antonio Ferrara, Alberto Rumi, Francesco BonchiLarge Language Model AlignmentBacktranslation Augmented Direct Preference Optimization

    Intesa Sanpaolo AI Research

  18. See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

    Sep 28, 2026Weiqiao Que, Ruizhe Li, Chengyu Wang +3Large Language Model SafetyEmergent Misalignment

    School of Computer Science and Technology, East China Normal University, China · School of Computer Science, University of Birmingham, UK · Alibaba Group, China +2

  19. Muon Sublates the Edge of Stability in LLM Pretraining

    Sep 28, 2026Yanzhe Chen, Qifang Zhao, Xiaoxiao Xu +1MuonLarge Language Model Alignment

    School of Mathematical Sciences, Shanghai Jiao Tong University, China · Alibaba Inc., Hangzhou, China · School of Mathematical Sciences, Institute of Natural Sciences and MOE-LSC, Shanghai Jiao Tong University, China

  20. DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models

    Sep 28, 2026Qirui Liu, Yichen Sun, Yan Wang +4Safety AlignmentLarge Language Model Alignment

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Ant Group · Chongqing Ant Consumer Finance Co., Ltd

  21. ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control

    Sep 28, 2026Eric Frankel, Banghua Zhu, Sewoong Oh +1Large Language Model AlignmentReinforcement Learning From Human Feedback

    University of Washington, Seattle

  22. The Alignment Illusion in Multimodal Large Language Models

    Sep 24, 2026Hong-Han Wang, Yuntao Wang, Hu DingMultimodal Large Language ModelsLarge Language Model Alignment

    University of Science and Technology of China, Hefei, China

  23. Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms

    Sep 24, 2026Rong Wang, Kun Sun, Yadong GuoLarge Language Model JudgesLarge Language Model Alignment

    University of Tübingen · Tongji University

  24. onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

    Sep 21, 2026Lei Yang, Mengyin Liu, Jia Wang +9Large Language Model AnnotationsLarge Language Model Alignment

    StepFun · Xiamen University

  25. Alignment Forecasting: Predicting Misalignment From Training Data

    Sep 19, 2026Chen Yueh-Han, Bruce W. Lee, Ilia Sucholutsky +1Large Language Model AlignmentMisalignment Persona

    NYU, MATS · Independent · NYU +1

  26. GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models

    Sep 16, 2026Alexander Didenko, Anna Shabanova, Vladislav Zapylikhin +2Cultural AwarenessLarge Language Model Alignment

    Artificial Intelligence Laboratory, SKOLKOVO School of Management, Moscow · Artificial Intelligence Laboratory, University of Tyumen · Institute of Business Studies, Russian Presidential Academy of National Economy and Public Administration, Moscow

  27. TAME: Token Attribution and Masking for Emergent misalignment

    Sep 15, 2026Md Rayhanul Masud, Md Rizwan ParvezEmergent MisalignmentLarge Language Model Alignment

    University of California, Riverside · 2Qatar Computing Research Institute (QCRI)

  28. Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue

    Sep 14, 2026Youyuan Zhang, Siyuan Li, Fangming Liu +1Large Language Model AlignmentPersistent State

    Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory, China · Huazhong University of Science and Technology, China

  29. Direct Preference Density Alignment for Conversational Audio Equalization

    Sep 14, 2026Ioannis Stylianou, Sven Ewan Shepstone, Jon Francombe +2Backtranslation Augmented Direct Preference OptimizationLarge Language Model Alignment

    Department of Electronic Systems Aalborg University Aalborg, Denmark · Bang & Olufsen A/S Struer, Denmark

  30. Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

    Sep 14, 2026Jiayi Yuan, Hangoo Kang, James Jihao Liu +4Large Language Model AlignmentMulti-Agent Reinforcement Learning

    University of Washington · 2Stanford University

  31. One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs

    Sep 14, 2026Naihao Deng, Samee Arif, Shuaichen Chang +2Algorithmic FairnessLarge Language Model Alignment

    University of Michigan · The Ohio State University · University of Aberdeen +1

  32. Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model

    Sep 12, 2026Hyojung HanLarge Language Model ResponsesLarge Language Model Alignment

    ThakiCloud

  33. An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

    Sep 12, 2026Roberto Campbell, Momin Abbass, Muneeza Azmat +5Large Language Model SafetyLarge Language Model Alignment

    University of California, Santa Cruz · IBM Research

  34. How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

    Sep 9, 2026Yi Shi, Tanyu Chen, Kai ShenSafety AlignmentLarge Language Model Alignment

    Continuum AI

  35. Suan: Rectifying Direct Preference Safety Alignment in Large Language Models

    Sep 8, 2026Oleksandr Cherednichenko, Roman KlypaSafety AlignmentLarge Language Model Alignment

    Department of Mathematics and Mathematical Statistics Integrated Science Lab, Umeå University Umeå, Sweden · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK 38000 Grenoble, France

  36. Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values

    Sep 8, 2026Yuemei Xu, Kexin Xu, Jian Zhou +3Human ValuesLanguage Pairs

    School of Information Science and Technology, Beijing Foreign Studies University · Beijing Academy of Artificial Intelligence · The State Key Lab of Software Development Environment, Beihang University

  37. From Echo Chambers to Epistemic Monoculture: Large Language Models Present Temporally Contingent Partisan Alignments as Knowledge

    Sep 7, 2026Wend K. TamPolitical DiscourseLarge Language Model Alignment

    National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign

  38. We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe Translation

    Sep 7, 2026Svetlana Gorovaia, Angelica Henestrosa, Ivan P. YamshchikovLarge Language Model AlignmentIdeology

    CAIRO, Technical University of Applied Sciences Würzburg-Schweinfurt Würzburg, Germany

  39. Representational alignment yields generalizable safety in language models

    Sep 3, 2026Lingyu Li, Yan Teng, Yingchun Wang +1Large Language Model SafetyLarge Language Model Alignment

    Shanghai Artificial Intelligence Laboratory, Shanghai, China

  40. Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

    Sep 3, 2026Hoang Cuong Nguyen, Mark Dras, Usman NaseemRefusalsLarge Language Model Alignment

    Macquarie University, Sydney, Australia

  41. SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

    Sep 3, 2026Caoyuan Ma, Tian Gu, Wenpu Liu +11Safety AlignmentLarge Language Model Alignment

    The University of Tokyo · Wuhan University · Shanghai AI Laboratory +4

  42. Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards

    Sep 3, 2026Leqi Zheng, Jinbo Su, Fang Niu +8Reinforcement Learning With Verifiable RewardLLM Reasoning Strategies

    Tsinghua University · Renmin University of China · Institute of Information Engineering, CAS +4

  43. Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour

    Sep 3, 2026Huixiang Fu, Marian-Andrei RizoiuMoral ReasoningHate Speech Detection

    Behavioral Data Science, University of Technology Sydney

  44. No country for old linguists: LLM-brain alignment underdetermines neural computation

    Sep 2, 2026Elliot MurphyLarge Language Model AlignmentArtificial Intelligence Alignment

    Vivian L. Smith Department of Neurosurgery, McGovern Medical School at UTHealth Houston, Houston, Texas, USA

  45. Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random

    Sep 1, 2026Cris HuynhLarge Language Model AlignmentItem Response Theory

    Independent researcher

  46. Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs

    Sep 1, 2026Jingshen Zhang, Shaoyang Xu, Wenxuan ZhangLarge Language Model AlignmentCultural Awareness

    School of Computer Science and Technology, Tianjin University · 2iNLP Lab, Singapore University of Technology and Design

  47. Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization

    Aug 31, 2026Dishu Yang, Jingjing Liu, Jize LiPrivacyLarge Language Model Alignment

    Khoury College of Computer Sciences Northeastern University San Jose, USA · Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley, USA · Department of Economics Boston University Boston, USA

  48. Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark

    Aug 30, 2026Abdullah Hashmat, Usman Naseem, Agha Ali RazaUrduLarge Language Model Alignment

    School of Computing, Macquarie University, Sydney, Australia · Lahore University of Management Sciences, Lahore, Pakistan

  49. Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment

    Aug 30, 2026Lingxiao Kong, Steffen Staab, Cong Yang +2Large Language Model AlignmentMulti-Objective Optimization

    Fraunhofer Institute for Applied Information Technology FIT · University of Cologne · University of Stuttgart +3

  50. When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs

    Aug 30, 2026Apoorva Upadhyaya, Sandipan SikdarMultilingual SafetyLarge Language Model Safety

    L3S Research Center, Leibniz Universität Hannover, Germany

  51. A Survey on Rubric-Guided Reinforcement Learning for Language Models

    Aug 27, 2026Zifei Shan, Fangning ShaoReinforcement Learning From Human FeedbackLarge Language Model Alignment

    WeChat, Tencent · Independent Researcher

  52. How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment

    Aug 12, 2026Guang Yang, Fengchen Liu, Alex Wang +2Large Language Model AlignmentRefusals

    University of California, Los Angeles · University of California, Berkeley · Stanford University

  53. Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

    Aug 12, 2026Mingyu Zong, Sampad Mohanty, Bhaskar KrishnamachariSafety AlignmentLarge Language Model Alignment

    Department of Computer Science University of Southern California Los Angeles, CA 90007

  54. Data Attribution of Emergent Misalignment with Persona Features

    Aug 11, 2026Clemens Vetter, David Kaczér, Lucie Flek +1Emergent MisalignmentLarge Language Model Alignment

    Bonn-Aachen International Center for Information Technology, University of Bonn, Germany

  55. Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

    Aug 10, 2026Alec Harris, Kasey Corra, Archie Chaudhury +1Large Language Model EvaluationLarge Language Model Alignment

    AI Safety Initiative at Georgia Tech · University of Chicago · Independent

  56. People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe

    Aug 7, 2026Maria-Louisa Wightman, Guillaume Bied, Tijl De BieHuman ValuesLarge Language Model Alignment

    Electronics and Information Systems (ELIS), Ghent University

  57. Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

    Aug 5, 2026Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1Safety AlignmentLarge Language Model Alignment

    University of Mannheim · Technical University Clausthal

  58. Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech

    Aug 3, 2026Shadab Bin Habib, A K M Ferdous Reza Habib, Subarno Neel +1Large Language Model SafetyLarge Language Model Alignment

    Department of Computer Science and Engineering Islamic University of Technology, Dhaka, Bangladesh

  59. Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese

    Aug 3, 2026Naho Orita, Hayato Ogawa, Daisuke KawaharaLarge Language Model BiasLanguage Pairs

    Waseda University

  60. Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer

    Aug 3, 2026Tyler Ashoff, Jordan RoduLarge Language Model AlignmentCross-Lingual Transfer

    Department of Statistics, University of Virginia. · Department of Statistics, University of Virginia