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

From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs
Sep 24, 2026Hanze Guo, Aixuan Song, Jing Yao +4LLM Alignment Personalized Language Models
Gaoling School of Artificial Intelligence, Renmin University of China · Microsoft Research Asia · Beijing Key Laboratory of Research on Large Models and Intelligent Governance +1
Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing
Sep 23, 2026Norah Almousa, Shayan Peyghambari Oskoui, Raquel Coelho +3LLM Evaluation LLM Alignment
University of Pittsburgh
Syndrome, Synergy, and Safety: Structured Reasoning and Knowledge-Driven Alignment for TCM Prescription Generation
Sep 22, 2026Zheng Chen, ZhiCheng Du, Haoxuan Li +1LLM Alignment CoT Reasoning
Tsinghua University · Guangdong Provincial Laboratory of Traditional Chinese Medicine Hengqin
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Sep 21, 2026Lei Yang, Mengyin Liu, Jia Wang +9LLM Alignment LLM-Assisted Annotation
StepFun · Xiamen University
Alignment Forecasting: Predicting Misalignment From Training Data
Sep 19, 2026Chen Yueh-Han, Bruce W. Lee, Ilia Sucholutsky +1LLM Alignment Emergent Misalignment in Language Models
NYU, MATS · Independent · NYU +1
Stress-testing Alignment Midtraining
Sep 17, 2026Sid Baines, Jonathan Bostock, Maria Angelica Martinez +3LLM Alignment Language Model Post-Training
Arcadia Impact · Resolution
Benchmarking LLM Compliance with China AI Generated Content Regulations
Sep 17, 2026Chenrui Cui, Hongye Fang, Lisha Song +3LLM Safety Benchmarks LLM Alignment
School of Computer Science and Technology, Tongji University, Shanghai, China · Law School of Tongji University, Shanghai, China
AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
Sep 16, 2026Sai Sri Pushpa Jampani, Kshitij Mishra, Asif EkbalLLM Alignment LLM Auditing
Indian Institute of Technology Patna, Bihar, India
A Zeroth-Order Paradigm for LLM Preference Alignment
Sep 16, 2026Peter Chen, Xi Chen, Wotao Yin +1Pairwise Preference Learning LLM Alignment
Department of Electrical Engineering and Computer Sciences (EECS) University of California, Berkeley Berkeley, CA 94720, USA · Stern School of Business New York University New York, NY 10012, USA · Decision Intelligence Lab (Seattle) DAMO Academy, Alibaba Group U.S. Bellevue, WA 98004, USA +1
Inoculation Midtraining with Learned Neologisms
Sep 14, 2026Kyle O'Brien, Edward James Young, Puria Radmard +4LLM Alignment LLM Safety
Geodesic Research · OpenAI · UK AI Security Institute
Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models
Sep 14, 2026JungMin Yun, Junehyoung Kwon, Hayeong Ryu +3LLM Alignment Direct Preference Optimization
Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University
Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking
Sep 14, 2026Arun Jose, Julian StastnyReward Hacking Fine-Tuning
Astra Fellowship · Redwood Research
Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue
Sep 14, 2026Youyuan Zhang, Siyuan Li, Fangming Liu +1Belief Revision LLM Alignment
Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory, China · Huazhong University of Science and Technology, China
Direct Preference Density Alignment for Conversational Audio Equalization
Sep 14, 2026Ioannis Stylianou, Sven Ewan Shepstone, Jon Francombe +2RL for Language Models LLM Alignment
Department of Electronic Systems Aalborg University Aalborg, Denmark · Bang & Olufsen A/S Struer, Denmark
Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
Sep 14, 2026Kazusato Oko, Annie Ulichney, Nika Haghtalab +1LLM Alignment Preference Alignment
One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs
Sep 14, 2026Naihao Deng, Samee Arif, Shuaichen Chang +2LLM Evaluation LLM Alignment
University of Michigan · The Ohio State University · University of Aberdeen +1
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families
Sep 13, 2026Orion Reblitz-RichardsonLLM Alignment Moral Reasoning in Language Models
Distiller Labs.
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
Sep 12, 2026Hyojung HanLLM Alignment LLM Auditing
ThakiCloud
How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE
Sep 9, 2026Yi Shi, Tanyu Chen, Kai ShenMixture-of-Experts Language Models LLM Alignment
Continuum AI
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
Sep 8, 2026Yunpeng Xu, Kun ZhengLLM Alignment Domain-Adaptive Pretraining
Suan: Rectifying Direct Preference Safety Alignment in Large Language Models
Sep 8, 2026Oleksandr Cherednichenko, Roman KlypaLLM Alignment LLM Safety Alignment
Department of Mathematics and Mathematical Statistics Integrated Science Lab, Umeå University Umeå, Sweden · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK 38000 Grenoble, France
From Echo Chambers to Epistemic Monoculture: Large Language Models Present Temporally Contingent Partisan Alignments as Knowledge
Sep 7, 2026Wend K. TamLLM Alignment LLM Interpretability
National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign
The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs
Sep 7, 2026Eric SoLLM Alignment Language Model Safety Evaluation
MIT Sloan School of Management Massachusetts Institute of Technology
Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts
Sep 7, 2026Kaicheng Zhang, Jingyi Xiao, Renjun Hu +3LLM Alignment LLM Safety Evaluation
East China Normal University Shanghai, China
No country for old linguists: LLM-brain alignment underdetermines neural computation
Sep 2, 2026Elliot MurphyLLM Alignment Neural Encoding
Vivian L. Smith Department of Neurosurgery, McGovern Medical School at UTHealth Houston, Houston, Texas, USA
Thinking effort aligns between humans and reasoning models in abductive reasoning
Sep 1, 2026Henry ArthurLLM Alignment Cognitive Modeling
Center for Mind/Brain Sciences, University of Trento, Italy
Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation
Sep 1, 2026Thibaut Thonet, Jos Rozen, Laurent BesacierLLM Alignment TTS Evaluation
NAVER LABS Europe
Post-hoc Alignment of LLM-judges to Human Judgment Distribution
Sep 1, 2026Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1Soft-Label Learning LLM Alignment
Amazon, Barcelona, Spain · Amazon, Berlin, Germany
Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation
Aug 31, 2026Alessio Galatolo, Meriem BeloucifPairwise Preference Learning LLM Alignment
Uppsala University
Mind the Gap: Theory-of-Mind-Grounded Friction for Epistemic Alignment
Aug 31, 2026Yifan Zhu, Kyeongmin Rim, James PustejovskyLLM Alignment Pragmatic Reasoning in Language Models
Brandeis University, Waltham, MA, USA

Sep 24, 2026, cs.AIJ/K move · Enter open · S save

From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs

Hanze Guo, Aixuan Song, Jing Yao, Xiangxu Zhang+3

Gaoling School of Artificial Intelligence, Renmin University of China · Microsoft Research Asia · Beijing Key Laboratory of Research on Large Models and Intelligent Governance+1

LLM Alignment Personalized Language Models Personalized Language Model Alignment Inference-Time Language Model Alignment User Preference Modeling

Open paper AskPDF arXiv

Personalized value alignment has become increasingly important as large language models (LLMs) are expected to accommodate diverse user preferences. However, existing methods typically align model outputs with a static value profile across prompts, overlooking that the salience of value dimensions varies substantially across contexts. Inspired by Lewin's Field Theory, which views human behavior as jointly shaped by personal dispositions and situational constraints, we model personal values as priors and context-dependent preferences as posteriors. We propose BaCVA, an inference-time Bayesian Context-aware personalized Value Alignment method that approximates posterior personalized preferences by integrating static personal values with scenario-specific value salience. BaCVA first estimates contextual value salience from generally normative responses, and then employs a dual-view personalization module to infer posterior preferences from complementary personal-value and scenario-driven perspectives. This Bayesian formulation enables more accurate and adaptive personalized value alignment while improving data efficiency via prior values. Extensive experiments on benchmarks demonstrate its superiority over strong baselines.

Momentum

Related topics

Latest papers 422