Artificial Intelligence Alignment

Ask about this topic

Momentum

8 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 99

All topics
CardsList

  1. SPEAR: Five Principles for Interactive Human-Agent Alignment

    Oct 5, 2026Tao Long, Lydia B. ChiltonArtificial Intelligence Alignment

    Columbia University New York City, New York, USA

  2. Referential Uncertainty in Human--AI Collaboration

    Sep 30, 2026Christian Poelitz, Finale Doshi-Velez, Siân LindleyHuman-Ai CollaborationHuman-Robot Collaboration

    Microsoft Research, Cambridge, UK · Harvard University, Cambridge, MA, USA

  3. Character Training for Risk-Averse Agents

    Sep 29, 2026Arav Dhoot, Punya Syon Pandey, Jamie Johnson +3Artificial Intelligence AlignmentAgentic Learning

    UK AI Security Institute · Resolution

  4. Which Attention Heads are like the Human Head? Not the Ones that Compute

    Sep 29, 2026Christopher Pinier, Gustaw Opiełka, Hannes Rosenbusch +3Artificial Intelligence AlignmentCode Completion

    Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands · Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA

  5. Constitutional adapters: Inference-time interventions for misalignment and misuse

    Sep 29, 2026Adam S. Lowet, Mark KurzejaArtificial Intelligence AlignmentLow-Rank Adaptation Adapters

    Anthropic Fellows Program · Independent

  6. Alignment Games: A Framework for Conceptual Repair in Human-AI Collaboration

    Sep 28, 2026Hari Subramonyam, Maneesh Agrawala, Sean FollmerArtificial Intelligence AlignmentHuman-Ai Collaboration

    Stanford University USA

  7. Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

    Sep 24, 2026Ruoqi Guo, Yi Liu, Gelei Deng +6Artificial Intelligence AlignmentAdversarial Evaluation

    Griffith University · Nanyang Technological University · UNSW +4

  8. Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner

    Sep 14, 2026Kazusato Oko, Annie Ulichney, Nika Haghtalab +1Reinforcement Learning From Human FeedbackArtificial Intelligence Alignment

  9. GUIDE: Generative Utility Inference and Decision Engine

    Sep 14, 2026Anagha Tiwari, Alexander G. Gray, Nick Feamster +3Preference Alignment LearningElicitation

    Department of Computer Science, University of Chicago · Centaur AI Institute, University of Chicago · Heinz College & School of Computer Science, Carnegie Mellon University +1

  10. 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

  11. Mechanism Design for Alignment and Control

    Sep 1, 2026Dirk Bergemann, Andrew Koh, Stephen MorrisIncentivesArtificial Intelligence Alignment

    Yale · Columbia · MIT +1

  12. The Assistant's Ideal Self

    Aug 31, 2026Mert YazanSelfArtificial Intelligence Alignment

    Leiden University · Research conducted at the Digital Minds Research Sprint, August 2026.

  13. Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment

    Aug 31, 2026Deepak Pandita, Christopher M. HomanArtificial Intelligence AlignmentHuman-Centered Framework

    Rochester Institute of Technology

  14. R2^2A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment

    Aug 30, 2026Mohan Zhang, Chengsong You, Xiaoyu Cao +4Behavioral Foundation ModelsArtificial Intelligence Alignment

    College of AI, Tsinghua University · 2Independent Researcher

  15. Automated Researchers Can Mitigate Well-characterized Alignment Failures

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

    1Anthropic Fellows Program · 2Anthropic · 3UC Berkeley

  16. AI Alignment through a Game-theoretic Lens: A Survey

    Aug 28, 2026Yanan Cai, Zhongrui Zhao, Zhigang Lu +6Artificial Intelligence AlignmentGame Theory

    James Cook University · Western Sydney University · Adelaide University +5

  17. MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment

    Aug 25, 2026Dongyue Li, Ziniu Zhang, Lu Wang +1Preference AlignmentMixture Models

    Northeastern University, Boston, MA · University of Michigan, Ann Arbor, MI

  18. Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

    Aug 17, 2026Ao Shen, Yongheng Zhang, Yinghui Li +3Latent Visual ReasoningLarge Multimodal Models

    Tencent Youtu Lab · Fudan University

  19. Synthetic Persona Pretraining: Alignment from Token Zero

    Aug 13, 2026Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12Artificial Intelligence AlignmentPersona Consistency

    EPFL · SJTU · Northeastern University +8

  20. Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales

    Aug 13, 2026Long Hoang Nguyen, Brice Valentin Kok-Shun, Guangyu Du +1Artificial Intelligence AlignmentFree-Form Textual Rationales

    1Technical University of Munich · University of Auckland

  21. Toward a Theory of Value in AI Alignment

    Aug 10, 2026Andrew Smart, Shazeda Ahmed, Jackie Kay +3Artificial Intelligence AlignmentHuman Values

    1Google Research · 2UCLA · 3Google Deep Mind +2

  22. Metanormative Theory for RL-Based Moral Agents

    Aug 8, 2026Aleks Knoks, Marija SlavkovikMoral ReasoningSocial Norms

    University of Luxembourg, 2, place de l’Université, L-4365, Esch-sur-Alzette, Luxembourg · University of Bergen, Fosswinckelsgt. 6, 5007 Bergen, Norway

  23. Human-AI Perceptual Alignment by Playing Hues and Cues

    Aug 7, 2026Nuria Alabau-Bosque, Jorge Vila-Tomás, Paula Daudén-Oliver +3PerceptuallyArtificial Intelligence Alignment

    Image Processing Lab, Universitat de València, Carrer del Catedrátic José Beltrán Martinez, Paterna, 46980, Spain

  24. CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

    Aug 6, 2026Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad +2Linear Activation SteeringSteering

    University of Southern California, Los Angeles, USA

  25. Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing Objectives

    Aug 6, 2026Keziah NaggitaHuman-Ai InteractionArtificial Intelligence Alignment

    TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO Chicago, Illinois

  26. Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems

    Aug 5, 2026Isaiah AndrewsRationalityArtificial Intelligence Alignment

    Department of Economics, Massachusetts Institute of Technology, and NBER

  27. The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk

    Aug 4, 2026Francis HeylighenArtificial Intelligence AlignmentHuman Values

    Center Leo Apostel, Vrije Universiteit Brussel

  28. AI Alignment and Fiduciary Obligation

    Aug 1, 2026Benjamin LangeArtificial Intelligence AlignmentEthics

    Ludwig-Maximilians-Universität München & Munich Center for Machine Learning

  29. Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization

    Jul 31, 2026Tyler Ashoff, Jordan RoduArtificial Intelligence AlignmentMultimodal Alignment

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

  30. Fragility of Value under Imperfect Alignment

    Jul 30, 2026Winter CrossArtificial Intelligence AlignmentHuman Values

    Dovetail Research

  31. Asymmetric Communication: Large Language Models and Language Games

    Jul 30, 2026Enzo FenoglioArtificial Intelligence AlignmentMoral Reasoning

    Dept. Computer Science University College London 66-72 Gower Street, London WC1E 6EA, UK

  32. MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing

    Jul 28, 2026Katsuya Ogata, Zongshang Pang, Mayu Otani +1Video EditingMulti-Image Editing Benchmarks

    1The University of Osaka · 2CyberAgent, Inc.

  33. Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

    Jul 22, 2026Haran Shani-Narkiss, Michael Fire, Oren TsurLarge Language Model BiasTask Framing

    University College London, London, England. · Ben-Gurion University of the Negev, Be’er Sheba, Israel.

  34. Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning

    Jul 20, 2026Vijay Keswani, Breanna K. Nguyen, Cyrus Cousins +3Artificial Intelligence AlignmentArtificial Intelligence Systems

    Department of Computer Science and Engineering, IIT Delhi · Department of Philosophy, Duke University · Department of Computer Science, Carnegie Mellon University +1

  35. A Method for Learning Value Systems in Generative AI

    Jul 18, 2026Andrés Holgado-Sánchez, Holger Billhardt, Sascha OssowskiArtificial Intelligence AlignmentGenerative Artificial Intelligence

    1CETINIA, University Rey Juan Carlos

  36. When Is Delegated Play Truthful? Within-Range Regret and the Trilemma of Aligned Delegation

    Jul 15, 2026Taksch DubeHonestyIncentives

    Kent State University, Kent, OH, USA

  37. Align AI to Dynamic Human-AI Workflows

    Jul 15, 2026Valerie Chen, Cleotilde Gonzalez, Anita Williams Woolley +4Human-Ai CollaborationArtificial Intelligence Alignment

    1Carnegie Mellon University · University of California, Irvine

  38. Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

    Jul 3, 2026Andreas Kouridakis, Dimitrios Patiniotis Spyropoulos, George VourosHuman-Ai CollaborationHuman-Centered Framework

    University of Piraeus Piraeus, Greece

  39. The Two Genie Game: Adoption and Welfare in Audit-Grounded AI Governance

    Jun 27, 2026Darrell Lewis-SandyAdoptionArtificial Intelligence Governance

  40. The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

    Jun 24, 2026Seth Dobrin, Łukasz ChmielArtificial Intelligence SafetyAuthorization

    ARYA Labs PBC

  41. A Taxonomy of Conceptual Alignment in Human-Robot Dialogue

    Jun 21, 2026Shengchen Zhang, Xiaohua Sun, Weiwei GuoHuman-Robot InteractionArtificial Intelligence Alignment

    College of Design and Innovation, Tongji University, Shanghai, China. · School of Design, Southern University of Science and Technology, Shenzhen, Guangdong, China.

  42. Quantifying Theoretical AI Alignment Guarantees: Receiver-Utility Bounds in Bayesian Persuasion

    Jun 20, 2026Eric Yachbes, Eva TardosArtificial Intelligence AlignmentPersuasion

    Cornell University, United States

  43. AI Alignment From Social Choice Perspectives

    Jun 19, 2026Daniel Halpern, Evi Micha, Ariel D. Procaccia +3Artificial Intelligence AlignmentReinforcement Learning From Human Feedback

    Google Research · University of Southern California · Harvard University

  44. Self-CTRL: Self-Consistency Training with Reinforcement Learning

    Jun 16, 2026Itamar Pres, Laura Ruis, Melat Ghebreselassie +2Artificial Intelligence AlignmentExplainable AI Methods

    MIT CSAIL

  45. Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

    Jun 10, 2026Sam MaoArtificial Intelligence AlignmentArtificial Intelligence Safety

    New York University | Interactive Media Arts

  46. Emergent alignment and the projectability of ethical personas

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

    University of Massachusetts Amherst · Indiana University Bloomington

  47. Sycophancy Towards Researchers Drives Performative Misalignment

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

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

  48. Building Comparative Motivation Profiles with Instrumental Interventions

    Jun 6, 2026David Vella Zarb, Rustem Turtayev, Taywon Min +2Artificial Intelligence AlignmentDeception

    MATS · University of Cambridge · KAIST +1

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

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

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

  50. What Do People Actually Want From AI? Mapping Preference Plurality

    Jun 4, 2026Julia Sepúlveda Coelho, Scott A. HaleArtificial Intelligence AlignmentPreference Alignment Learning

    Oxford Internet Institute, University of Oxford, United Kingdom · Meedan, United States

  51. A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI

    May 29, 2026Atahan KaragozArtificial Intelligence AlignmentGenerative Artificial Intelligence

    Department of Computer Science University of Basel Basel, Switzerland

  52. TUX: Measuring Human--AI Tacit Understanding

    May 29, 2026Yueshen Li, Hanyi Min, Vedant Das Swain +1Artificial Intelligence Alignment

    University of Illinois Urbana-Champaign · New York University

  53. EUDAIMONIA: Evaluating Undesirable Dynamics in AI

    May 28, 2026Jun Rui Huang, Wang Bill Zhu, Ziyi Liu +3Artificial Intelligence AlignmentConversational Context

    University of Southern California

  54. Rationalize: Shared Semantic Reasoning for Human-AI Alignment

    May 28, 2026Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi +3Artificial Intelligence AlignmentHuman-Ai Collaboration

    New Jersey Institute of Technology Newark, USA

  55. In-Context Reward Adaptation for Robust Preference Modeling

    May 28, 2026Zhenyu Sun, Zheng Xu, Ermin WeiReinforcement Learning From Human FeedbackPreference Alignment Learning

    Northwestern University · Meta Superintelligence Labs

  56. Gram: Assessing sabotage propensities via automated alignment auditing

    May 28, 2026David Lindner, Victoria Krakovna, Sebastian FarquharSabotageArtificial Intelligence Alignment

    1Google DeepMind

  57. Toward AI That Understands Self and Others: A World-Model Theory of Cognitive Diversity and Alignment

    May 28, 2026Toru TakahashiArtificial Intelligence AlignmentCognitive Science

    Human Informatics and Systems Lab, Doshisha University · Linked Open Data Initiative, NPO · Keio Research Institute at SFC +1

  58. Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation

    May 28, 2026Zixuan Jiang, Yanqiao Zhu, Peng Wang +8Automatic Speech RecognitionCharacter Error Rate

    College of Artificial Intelligence, Xi’an Jiaotong University, Xi’an 710049, China · X-LANCE Lab, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China · The Chinese University of Hong Kong, Shenzhen, Shenzhen 518172, China +2

  59. Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization

    May 27, 2026Aarik GulayaArtificial Intelligence AlignmentHuman-Ai Interaction

    Base Layer

  60. Voluntary Collusion with Secret Tools in Competing LLM Agents

    May 26, 2026Xijie Zeng, Frank RudziczCollusionLarge Language Model Agents

    Dalhousie University · Vector Institute for Artificial Intelligence