Misalignment

Ask about this topic

Recent momentum

-67%

5 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Also in Value Alignment

Neighbouring directions

Large Language Model AlignmentValue AlignmentArtificial Intelligence AlignmentFeature AlignmentBehavioral Alignment

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Misalignment.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Misalignment.

98 papers

Latest in Misalignment

Open your feed →
CardsList

  1. Flexible-body Modeling, Kinematic Identification, and Assembly Accuracy of Overconstrained Spatial Linkages

    Sep 15, 2026Daniel Huczala, Michael Pieber, Johannes Gerstmayr +6Kinematic ChainRigid-Body Dynamics

  2. TAME: Token Attribution and Masking for Emergent misalignment

    Sep 15, 2026Md Rayhanul Masud, Md Rizwan ParvezMisalignmentLarge Language Model Alignment

  3. Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking

    Sep 14, 2026Arun Jose, Julian StastnyTraining-Free Reward AlignmentHarmful Fine-Tuning

  4. The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs

    Sep 7, 2026Eric SoMisalignmentIntrinsic Motivation

  5. When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

    Sep 1, 2026Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2FragilityFinetuning

  6. Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment

    Sep 1, 2026Mohamad Jouni, Aurélien Godet, Mauro Dalla MuraHyperspectral Image Super-ResolutionHyperspectral Imaging

  7. When 3D Gaussian Splatting Recovers Real Surfaces

    Aug 30, 2026Songhe Wang, David Johnathan Miller3D Gaussian SplatsHigh-Fidelity Surface Reconstruction

  8. Automated Researchers Can Mitigate Well-characterized Alignment Failures

    Aug 28, 2026Chen Yueh-Han, Jiaxin Wen, Jan Hendrik KirchnerArtificial Intelligence AlignmentMisalignment

  9. Data Attribution of Emergent Misalignment with Persona Features

    Aug 11, 2026Clemens Vetter, David Kaczér, Lucie Flek +1MisalignmentHarmful Fine-Tuning

  10. Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment

    Aug 8, 2026Peiyang Liu, Xi Wang, Ziqiang Cui +2MisalignmentHarms

  11. Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG

    Aug 5, 2026Shiwen Chu, Shanglin Li, Motoaki Kawanabe +1Domain AdaptationMotor Imagery

  12. MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding

    Aug 4, 2026Ruirui Zhang, Zhengkai Zhao, Pan GaoPersonalizationMisalignment

  13. Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models

    Aug 3, 2026Linkai Peng, Baorian NuchgedReadoutLogit Lens

  14. NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability

    Jul 31, 2026Duo Xu, Faramarz FekriNeuro-Symbolic FrameworkLarge Language Model Agents

  15. Fragility of Value under Imperfect Alignment

    Jul 30, 2026Winter CrossArtificial Intelligence AlignmentHuman Values

  16. PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

    Jul 30, 2026Manyi Wang, Junjielong Xu, Pinjia HeSwe-Bench VerifiedMisalignment

  17. CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

    Jul 29, 2026Behraj Khan, Shabir Ahmad, Syed Ahmad Chan Bukhari +1Covariate ShiftLatent Bridge Matching

  18. Misalignment Has a Personality: A Big Five Account of Emergent Misalignment

    Jul 29, 2026Hasibur Rahman, Smit DesaiMisalignmentPersonality

  19. Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems

    Jul 28, 2026Marylou Fauchard, Florian Carichon, Margarida Carvalho +1Multi-Agent SystemsDeception

  20. COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution

    Jul 28, 2026Jincheng Wang, Min Zheng, Tao WeiAgentic WorkflowsWorkflow Automation and Optimization

  21. Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension

    Jul 27, 2026Jinhao Zhang, Zeyu Liu, Zicheng Yan +4Residual ConnectionsResidual Learning

  22. Emergent Misalignment Recruits a Pre-existing Persona Subspace

    Jul 23, 2026Mohammed Suhail B NadafMisalignmentHarmful Fine-Tuning

  23. Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

    Jul 21, 2026Aarushi SinghLarge Language Model SafetyUntrusted Input

  24. How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA

    Jul 17, 2026Navya Gupta, Bingjie Xu, Avinash Anand +2Reasoning FailuresMisalignment

  25. An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?

    Jul 10, 2026Abhinav Rao, Liancheng Gong, Bin Hu +1MisalignmentLarge Language Model Alignment

  26. Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

    Jul 9, 2026Lu Dai, Ziyang Rao, Yili Wang +3MemorizationKnowledge Gaps

  27. Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5

    Jul 5, 2026Lyndon Drake, Zandi EberstadtMisalignmentLarge Language Model Alignment

  28. Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors

    Jul 1, 2026Yangfan Hu, Xuhan Tong, Haoyue Bai +5Large Language Model HallucinationHallucinations

  29. Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment

    Jun 30, 2026Jason R. Brown, Patrick Leask, Lev McKinneyLarge Language Model AlignmentMisalignment

  30. Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

    Jun 29, 2026Max Fomin, Elad David, Amit LeViIntrospection AdaptersSituation

  31. Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors

    Jun 29, 2026Maxime Riché, Daniel Tan, Vili Kohonen +1MisalignmentIndirect Prompt Injection

  32. Real-Time Compliance and Position Control of a Hyper-redundant Soft Robotic Arm

    Jun 29, 2026Runze Zuo, Tianhua Zou, Naike Wu +2Soft RobotsArms

  33. Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding

    Jun 25, 2026Liu Yu, Can Chen, Ping Kuang +3Large Vision Language ModelsHallucinations

  34. Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment

    Jun 24, 2026Aditya Singh, Gerson Kroiz, Senthooran Rajamanoharan +1MisalignmentDigital Forensics

  35. Probing the Misaligned Thinking Process of Language Models

    Jun 23, 2026Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2Large Language Model AlignmentMisalignment

  36. NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling

    Jun 22, 2026Jaehyun Cho, YoungJoon YooImage RegistrationImage Denoising

  37. Subspace-Constrained Federated Learning with Low-Rank Adaptation

    Jun 21, 2026Neranjan Senarath, Rohit Muralitharan, Sadia AsifFederated LearningLow-Rank Adaptation

  38. The Alignment Problem in Constrained Code Generation

    Jun 19, 2026Matteo Biagiola, Jahrim Gabriele Cesario, Luca Di Grazia +2Code GenerationLarge Language Model Performance

  39. What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data

    Jun 18, 2026Yuchen Zhang, Anietta Weckauff, Diego Garcia-Olano +1MisalignmentTraining-Inference Mismatch

  40. Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families

    Jun 18, 2026Abdul Rafay SyedMisalignmentLarge Language Model Alignment

  41. Emergent Alignment

    Jun 17, 2026Martin KolářLarge Language Model AlignmentMisalignment

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

    Jun 17, 2026Naihao Deng, Yiming Feng, Chimaobi Okite +4Large Language Model AlignmentMisalignment

  43. GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving

    Jun 15, 2026Ziying Song, Caiyan Jia, Lin Liu +3Multi-Sensor FusionBird'S-Eye View

  44. Human-like autonomy emerges from self-play and a pinch of human data

    Jun 11, 2026Daphne Cornelisse, Julian Hunt, Zixu Zhang +4Self-PlayNaturalistic Driving Data

  45. The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

    Jun 9, 2026Filippo Tonini, Federico Torrielli, Anton Danholt Lautrup +3ArbitrationMisalignment

  46. Emergent alignment and the projectability of ethical personas

    Jun 8, 2026Guillermo Del Pinal, Youngchan Lee, Calum McNamara +1Artificial Intelligence AlignmentMisalignment

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

    Jun 8, 2026Sicheng Wang, Xiangyang Zhu, Han Wang +6Harmful Fine-TuningMisalignment

  48. Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation

    Jun 7, 2026Qi Cao, Jian Lou, Meiting Liu +4Activation SteeringMisalignment

  49. Sycophancy Towards Researchers Drives Performative Misalignment

    Jun 7, 2026David D. Baek, Xinnuo Li, Anay Gupta +4SycophancyArtificial Intelligence Alignment

  50. The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment

    Jun 7, 2026Xiaoyang Wang, Christopher C. YangMulti-Agent DebateDebate

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

    Jun 6, 2026Manuele Reani, Hongyu TianArtificial Intelligence AlignmentConversational Artificial Intelligence

  52. The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

    Jun 4, 2026Jiachen Zhao, Zhengxuan Wu, Aryaman Arora +3MisalignmentHypothesis

  53. Consistency Training Along the Transformer Stack

    Jun 4, 2026Sukrati Gautam, Neil Shah, Arav Dhoot +7Safety AlignmentMisalignment

  54. Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment

    Jun 4, 2026Arush Tagade, Shaoheng Zhou, Jiaxin Wen +1Harmful Fine-TuningMisalignment

  55. (Mis)generalization of Helpful-only Fine-tuning

    Jun 3, 2026Mohammad Omar Khursheed, Baram Sosis, Fabien RogerHarmful Fine-TuningFinetuning

  56. Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

    May 31, 2026Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe +1Harmful Fine-TuningMisalignment

  57. Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards

    May 29, 2026Magnus Jørgenvåg, David Kaczér, Lasse Ruttert +3Training-Free Reward AlignmentMisalignment

  58. Equivariant Latent Alignment via Flow Matching under Group Symmetries

    May 29, 2026Sunghyun Kim, Jaehoon Hahm, Jeongwoo Shin +1Hierarchical Flow MatchingExact Equivariance

  59. Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models

    May 28, 2026Leijiang Gu, Zhen Zeng, Feng Li +2Multimodal Knowledge EditingMulti-Modal Large Language Models

  60. How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

    May 28, 2026Ningzhi Tang, Chaoran Chen, Gelei Xu +5Coding AgentsMisalignment