Pluralistic Alignment

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 27

All topics

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
Sep 22, 2026David Tsoi, Esra DönmezPluralistic Alignment Trade-Off
Department of Computer Science, University of Stuttgart · Institute for Natural Language Processing, University of Stuttgart · Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart
OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
Aug 31, 2026Hamed Babaei Giglou, Sören Auer, Peio Popov +2Ensemble Pluralistic Alignment
TIB Leibniz Information Centre for Science and Technology, Hannover, Germany · L3S Research Center, Leibniz University of Hannover, Hannover, Germany · Graphwise, Sofia, Bulgaria +1
Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment
Aug 12, 2026Haokai Zhao, Yunze Xiao, Weihao Xuan +3Sycophancy Pluralistic Alignment
University of New South Wales · Carnegie Mellon University · University of Tokyo
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
Aug 4, 2026Matt Ratto, Abhishek Moturu, Daniel SilverPluralistic Alignment Socio-Technical Systems
Faculty of Information, University of Toronto, Ontario, Canada · Massey College, Ontario, Canada · Schwartz Reisman Institute for Technology and Society, University of Toronto, Ontario, Canada +4
A Roadmap to Impactful Pluralistic Alignment Research
Jul 24, 2026Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh +3Pluralistic Alignment Internal Pluralism
1Massachusetts Institute of Technology · University of Washington · 3Carnegie Mellon University
Rushes: A Human Preference Dataset for Pluralistic Alignment
Jul 22, 2026Michael Xu, Jorge Leandro, Sudha Rao +5Preference Datasets Pluralistic Alignment
Microsoft Research
LKValues: Aligning Large Language Models with Sri Lankan Societal Values
Jul 22, 2026Nethmi Muthugala, Supryadi, Surangika Ranathunga +7Large Language Model Alignment Human Values
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand · Department of Computer Science & Engineering, University of Moratuwa, Sri Lanka +2
ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs
Jul 15, 2026Aryan Keluskar, Amrita Bhattacharjee, Huan LiuLarge Language Model Safety Agentic Deployments
School of Computing & AI, Arizona State University, Tempe, AZ, USA.
PLURAL: A Global Dataset for Value Alignment
Jul 9, 2026Dhruv Agarwal, Anya Shukla, Tanya Goyal +1Preference Datasets Pluralistic Alignment
Cornell University
Position: Align AI to Our Aspirations, Not Our Flaws
Jun 11, 2026Nikita Kazeev, Bui Nhat Huyen PhanPluralistic Alignment Internal Pluralism
1National University of Singapore · 2Shopee Singapore.
Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents
Jun 8, 2026Cheonsu JeongAutonomous Agents Pluralistic Alignment
AX Center, SAMSUNG SDS, Seoul, South Korea
Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
May 29, 2026Arkadiy Saakyan, Charvi Rastogi, Lora AroyoCultural Awareness Multilingual Safety
Columbia University, New York, NY, USA. · Google DeepMind, New York, NY, USA.
A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
May 29, 2026Atahan KaragozArtificial Intelligence Alignment Generative Artificial Intelligence
Department of Computer Science University of Basel Basel, Switzerland
Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA
May 24, 2026Jinyan Su, Jennifer HealeyClarification Multi-Turn Interactions
1Cornell University · 2Adobe Research
AvAtar: Learning to Align via Active Optimal Transport
May 23, 2026Qi Yu, Ruizhong Qiu, Zhichen Zeng +3Distributional Alignment Pluralistic Alignment
University of Illinois Urbana-Champaign · University of Florida · 3Arizona State University
From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
May 14, 2026Varad Vishwarupe, Nigel Shadbolt, Marina JirotkaPluralistic Alignment Internal Pluralism
Department of Computer Science, University of Oxford · Institute for Ethics in AI, University of Oxford · Responsible Technology Institute, University of Oxford
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
May 14, 2026Pengyun Zhu, Yuqi Ren, Zhen Wang +2Pluralistic Alignment Large Language Model Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China
When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
May 6, 2026Jiechen Li, Catherine A. Barry, Rishika Randev +3Sycophancy Epistemic Integrity
Duke University Durham, NC 27708 · ∗These authors contributed equally.
Misaligned by Reward: Socially Undesirable Preferences in LLMs
May 6, 2026Gayane Ghazaryan, Esra DönmezLarge Language Model Alignment Large Language Model Bias
Institute for Natural Language Processing, University of Stuttgart · 2Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart
Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy
May 2, 2026Rachel FreedmanPluralistic Alignment Lock-In
Department of Electrical Engineering and Computer Science, University of California, Berkeley, USA.
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
Apr 22, 2026Travis LaCroixPluralistic Alignment Artificial Intelligence Governance
Durham University, United Kingdom
Jailbreaking Large Language Models with Morality Attacks
Apr 18, 2026Ying Su, Mingen Zheng, Weili Diao +1Large Language Model Jailbreaks Moral Reasoning
South China University of Technology1 · HKUST2 · Beihang University3
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
Apr 16, 2026Yuxiang Wang, Hongyu Liu, Yijiang Xu +9Speech Language Models Pluralistic Alignment
1The Chinese University of Hong Kong, Shenzhen · 2Shenzhen Loop Area Institute · 3Amphion Technology Co., Ltd.
VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
Jan 19, 2026Shenyan Zheng, Jiayou Zhong, Anudeex Shetty +3Pluralistic Alignment Large Language Model Alignment
University of Waterloo · University of Melbourne · Macquarie University +2
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
May 30, 2025Jingyan Shen, Jiarui Yao, Rui Yang +5Large Language Model Personalization Preference Alignment Learning
New York University · University of Illinois Urbana-Champaign · Rice University
Societal Alignment Frameworks Can Improve LLM Alignment
Feb 27, 2025Karolina Stańczak, Nicholas Meade, Mehar Bhatia +14Large Language Model Alignment Pluralistic Alignment
ETH Zurich, Zurich, Switzerland · Mila, McGill University, Montreal, Canada · Université de Montréal, Montreal, Canada +12
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
Date pendingHaolong Hu, Hanyu Li, Tiancheng He +6Mllm-Based Large Language Model Alignment
Huazhong University of Science and Technology · Beijing University of Posts and Telecommunications · West China Biomedical Big Data Center, Sichuan University +2

Sep 22, 2026, cs.AIJ/K move · Enter open · S save

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment

David Tsoi, Esra Dönmez

Department of Computer Science, University of Stuttgart · Institute for Natural Language Processing, University of Stuttgart · Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart

Pluralistic Alignment Trade-Off Steering Dial

Open paper AskPDF arXiv

People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable models that can balance competing objectives differently. Multi-Objective Direct Preference Optimization (MODPO) does this by using an objective weight to span a continuum of trade-offs. We study two questions: when can one model improve two objectives simultaneously, and how can many trade-offs be covered without training a separate model for each? Across seven objective pairs from HelpSteer and UltraFeedback, two pre-training measurements predict whether objectives align or conflict for human-annotated data, but not for AI-annotated data, where response length and repetition confound reward-model scores. For broader trade-off coverage, selecting the nearest trained model and merging model parameters both help, but neither consistently matches direct training. These findings yield practical guidance for building steerable models that serve diverse preferences.

Momentum

Related topics

Latest papers 27