LLM Alignment

LLM: Large Language Model

Follow this topic 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

Latest papers 422

All topics

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
May 18, 2026Yanyun Wang, Yu Huang, Zi Liang +2LLM Alignment Audio-Language Models
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong Polytechnic University · The Chinese University of Hong Kong
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM $Δ$ Integration into Upcycled MoE
May 18, 2026Hao Zhou, Tianhao Li, Zhijun Wang +6Multilingual Language Models Mixture-of-Experts Language Models
National Key Laboratory for Novel Software Technology, Nanjing University · Tongyi Lab, Alibaba Group · Zhejiang University
Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
May 17, 2026Yucong Huang, Xiucheng Li, Kaiqi Zhao +1Reward Modeling LLM Alignment
Harbin Institute of Technology, Shenzhen, China.
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
May 16, 2026Weicheng XueLLM Alignment LLM Auditing
Virginia Tech
Alignment Drift in Long-Term Human-LLM Interaction: A Mechanism-Oriented Framework
May 15, 2026Xintong YaoLLM Alignment Human-AI Interaction
From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
May 14, 2026Varad Vishwarupe, Nigel Shadbolt, Marina JirotkaLLM Sycophancy LLM Alignment
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 +2LLM Alignment Pluralistic Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
May 14, 2026Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4LLM Alignment On-Policy Self-Distillation
1UC Riverside · 2International Computer Science Institute · 3Microsoft,∗ +1
Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
May 13, 2026Ye Wang, Jing Liu, Toshiaki Koike-AkinoReward Hacking LLM Alignment
Mitsubishi Electric Research Laboratories (MERL) · Broadway, Cambridge, MA 02139, USA
Probing Persona-Dependent Preferences in Language Models
May 13, 2026Oscar Gilg, Pierre Beckmann, Daniel Paleka +1LLM Alignment LLM Interpretability
MATS · MATS, EPFL · ETH Zürich +1
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
May 13, 2026Adil AminLLM Alignment LLM Interpretability
ZEHEN Labs
Persona-Model Collapse in Emergent Misalignment
May 13, 2026Davi Bastos Costa, Renato VicenteLLM Alignment LLM Fine-Tuning
TELUS Digital Research Hub · Center for Artificial Intelligence and Machine Learning · Institute of Mathematics, Statistics and Computer Science +1
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
May 12, 2026Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak +3Supervised Fine-Tuning LLM Alignment
Carnegie Mellon University
Learning Transferable Latent User Preferences for Human-Aligned Decision Making
May 12, 2026Alina Hyk, Sandhya SaisubramanianLLM Alignment LLM Decision-Making
Oregon State University
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
May 12, 2026Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van +3Pairwise Preference Learning LLM Alignment
Hanoi University of Science and Technology · University of Stuttgart · German Research Center for Artificial Intelligence +3
A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
May 12, 2026Haibo Chen, Xin Wang, Jiaheng Chao +2LLM Alignment Graph Representation Learning
Tsinghua University
To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands
May 12, 2026Fangyi Yu, Nabeel Seedat, Jonathan Richard Schwarz +1LLM Alignment Language Model Safety Evaluation
Thomson Reuters Foundational Research, 5 Canada Square, London · Imperial College London · University of Oxford
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
May 12, 2026Wenhao Chen, Sirui Sun, Shengyuan Bai +1LLM Alignment LLM Safety Alignment
School of Electronics Engineering and Computer Science, Peking University · Yuanpei College, Peking University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University
StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
May 12, 2026Ishmam Khan, Sindhuja Thogarrati, Shuo ZhangLLM Alignment LLM Fine-Tuning
Tufts University · Bose Corporation
A Mechanistic Investigation of Supervised Fine Tuning
May 12, 2026Ruhaan ChopraSupervised Fine-Tuning LLM Alignment
Independent Researcher
Leveraging RAG for Training-Free Alignment of LLMs
May 11, 2026John T. HalloranLLM Alignment LLM Safety Alignment
Leidos
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
May 11, 2026Christian Moya, Alex Semendinger, Guang Lin +1Pairwise Preference Learning LLM Alignment
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
May 11, 2026Mengyi Deng, Zhiwei Li, Xin Li +4LLM Alignment Reasoning Consistency in Language Models
1Information Hub, The Hong Kong University of Science and Technology (Guangzhou), China · 2The Hong Kong University of Science and Technology, Hong Kong SAR
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
May 11, 2026Huynh Trung Kiet, Dao Sy Duy Minh, Tuan Nguyen +5LLM Alignment Cultural Alignment
Faculty of Information and Technology, University of Science, Vietnam National University, Ho Chi Minh City, Vietnam. · Department of Computer Science, University of Warwick, Coventry, United Kingdom. · School of Computing, Engineering and Digital Technologies, Teesside University, United Kingdom.
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
May 11, 2026Krishak Aneja, Manas Mittal, Anmol Goel +2LLM Alignment LLM Interpretability
International Institute of Information Technology, Hyderabad · TU Darmstadt · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi
Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
May 11, 2026Junyu Lu, Deyi Ji, Xuanyi Liu +5Annotator Disagreement LLM Alignment
School of Computer Science and Technology, Dalian University of Technology, China · Tencent · Peking University +1
Positive Alignment: Artificial Intelligence for Human Flourishing
May 11, 2026Ruben Laukkonen, Seb Krier, Chloé Bakalar +13LLM Alignment AI Alignment
Department of Psychiatry, University of Oxford · 2Flourishing Intelligence Program, Centre for Eudaimonia and Human Flourishing,2026 Linacre College, University of Oxford · 4LIFE +10
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
May 11, 2026Wu Li, Yigeng Zhou, Zesheng Shi +3LLM Alignment Self-Play RL
Harbin Institute of Technology, Shenzhen, China · Beijing Academy of Artificial Intelligence, Beijing, China
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
May 11, 2026Sushrita Rakshit, Hanwen Zhang, Hua ShenLLM Alignment LLM Auditing
New York University · New York City, NY 10012 · New York University Shanghai
Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity
May 9, 2026Enoch Hyunwook KangLLM Alignment Personalized Language Model Alignment
Foster School of Business, University of Washington, Seattle, Washington, USA.

May 18, 2026, cs.CRJ/K move · Enter open · S save

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models

Yanyun Wang, Yu Huang, Zi Liang, Xixin Wu+1

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong Polytechnic University · The Chinese University of Hong Kong

LLM Alignment Audio-Language Models LLM Jailbreak Attacks

Open paper AskPDF arXiv

The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to embed harmful content into the audio signal. In this work, we challenge this necessity and propose a new paradigm in which the role of audio shifts from content injection to safety alignment interference. We reveal that LALM safety alignment can be compromised solely by specific Acoustic Latent Semantics (ALS), the underlying paralinguistic features intrinsic to the priors of audio generative models. Distinct from previous works that leverage explicit acoustic parameters to merely style malicious audio, we demonstrate that interference audio, benign in content but infused with specific ALS, can serve as a universal jailbreak trigger. Leveraging this insight, we propose the Acoustic Interference Attack (AIA), which decouples the attack payload from the audio. Specifically, AIA employs a set of universal, instruction-neutral interference audio, enabling standard malicious text queries to bypass safety alignment without instance-specific optimization. Extensive experiments on 10 LALMs across five datasets demonstrate that AIA achieves the state-of-the-art attack success rate. Furthermore, our interpretability analysis uncovers the inference path drift induced by AIA and identifies the inherent effective patterns within ALS, revealing the fundamental vulnerability of cross-modal alignment in LALMs.

Momentum

Related topics

Latest papers 422