LLM Alignment

LLM: Large Language Model

LLM alignment studies how to shape language models’ behavior so they are helpful, truthful, safe, and responsive to the people and settings they serve. Common approaches include supervised fine-tuning, preference learning such as Direct Preference Optimization, reinforcement learning from human or AI feedback, and inference-time steering or retrieval. Researchers evaluate these methods on instruction-following, preference, jailbreak, factuality, multilingual, and multi-turn tasks, while also developing ways to represent disagreement among users and communities. A central challenge is that gains in safety or preference alignment may reduce usefulness, diversity, calibration, or capability, and desired behavior may not generalize to new prompts, groups, or deployment settings.

Latest papers

613 papers58 papers in the last four weeks, up 12% on the four weeks before. 0.3% of all new papers.

Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes
Jan 8, 2026Yonghyun Jun, Junhyuk Choi, Jeonghyun Park +3LLM Alignment Personality Modeling in Language Models
Chung-Ang University, Seoul, Korea
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Jan 7, 2026Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2LLM Safety Benchmarks LLM Alignment
Advanced Knowledge Center for Immersive Technologies (AKCIT) Federal University of Goiás (UFG)
Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
Jan 7, 2026Guanyu Chen, Chenxiao Yu, Xiyang HuLLM Evaluation LLM Alignment
Arizona State University · University of Southern California
Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models
Jan 6, 2026Zhibo Hu, Chen Wang, Yanfeng Shu +2LLM Alignment Emergent Misalignment in Language Models
The University of New South Wales · CSIRO Data61
HAL: Inducing Human-likeness in LLMs with Alignment
Jan 6, 2026Masum Hasan, Junjie Zhao, Ehsan HoqueReward Modeling LLM Alignment
University of Rochester
ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
Jan 6, 2026Kapil Wanaskar, Gaytri Jena, Vinija Jain +2LLM Alignment Inference-Time Language Model Alignment
San José de State University, USA · Pragya Lab, BITS Pilani Goa, India · Google, USA +1
AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
Dec 18, 2025Aniruddha Roy, Jyoti Patel, Aman Chadha +2Language Model Merging LLM Alignment
HCL · Evalueserve · Apple (USA) +2
Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization
Dec 12, 2025Mélissa Tamine, Otmane Sakhi, Benjamin Heymann +2LLM Alignment Shapley Value Attribution
Criteo AI lab, FairPlay joint team, France · CREST, ENSAE, Institut Polytechnique de Paris · Criteo AI Lab, France +1
Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts
Dec 3, 2025Yijun LiaoLLM Alignment Direct Preference Optimization
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
Nov 26, 2025Zhenchao Tang, Fang Wang, Haohuai He +13LLM Alignment LLM Fine-Tuning
Tencent AI for Life Sciences Lab, Shenzhen, China. · Sun Yat-sen University, Shenzhen, China. · The Hong Kong Polytechnic University, Hong Kong SAR, China. +2
Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Nov 22, 2025Kartik Garg, Shourya Mishra, Kartikeya Sinha +8Deception in Language Models LLM Alignment
Pragya Lab, BITS Pilani Goa, India · Apple, USA · Google, USA
Value Drifts: Tracing Value Alignment During LLM Post-Training
Oct 30, 2025Mehar Bhatia, Shravan Nayak, Gaurav Kamath +4LLM Alignment Preference Optimization
Mila - Quebec AI Institute · McGill University · Université de Montréal +4
OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
Oct 28, 2025Ziyou Hu, Zhengliang Shi, Minghang Zhu +5Reward Modeling RL for Language Models
Leiden University, Leiden, Netherland · Shandong University, Qingdao, China · Tsinghua University, Beijing, China
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
Oct 20, 2025Tiancheng Hu, Benjamin Minixhofer, Nigel CollierLLM Alignment Model Calibration
University of Cambridge
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
Oct 15, 2025Pardis Sadat Zahraei, Gokhan Tur, Dilek Hakkani-Tür +1LLM Alignment Refusal Behavior in Language Models
University of Illinois Urbana-Champaign (UIUC) · Qatar Computing Research Institute (QCRI), Hamad Bin Khalifa University
Hierarchical Alignment: Block-Level LoRA-DPO for Preference Tuning in Large Language Models
Oct 14, 2025Yishen Chen, Qi Dong, Yukun ZhangLLM Alignment Preference Alignment
Fudan University Shanghai, China · The Chinese University of Hong Kong Hong Kong, China
Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
Oct 11, 2025Pratik S. Sachdeva, Tom van NuenenLLM Decision-Making Moral Reasoning in Language Models
D-Lab, University of California, Berkeley
Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences
Oct 7, 2025Batu El, James ZouLLM Alignment LLM Safety
Stanford University
TagPR: Tag-Guided Process Supervision for Personalization Reasoning in Large Language Models
Sep 27, 2025Song Jin, Juntian Zhang, Ruyu Lyu +7LLM Alignment LLM Personalization
Gaoling School of Artificial Intelligence, Renmin University of China · Meituan · Wuhan University
From Value Conditioning to Behavioral Shift: Lightweight Value Alignment of LLMs
Aug 15, 2025Shangrui Nie, Florian Mai, David Kaczér +3LLM Alignment Supervised Fine-Tuning
Conversational AI and Social Analytics (CAISA) Lab, University of Bonn, Germany · McMaster University, Canada · Department of Computer Science, University of Sheffield, United Kingdom
ESSA: Evolutionary Strategies for Scalable Alignment
Jul 6, 2025Daria Korotyshova, Boris Shaposhnikov, Alexey Malakhov +7LLM Alignment Evolutionary Optimization
T-Tech · Yandex
A Technical Survey of Reinforcement Learning Techniques for Large Language Models
Jul 5, 2025Saksham Sahai Srivastava, Vaneet AggarwalRL for Language Models LLM Alignment
University of Georgia, Athens, GA, USA · Purdue University, West Lafayette, IN, USA
Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
Jun 30, 2025Tung-Ling Li, Hongliang LiuLLM Alignment Language Model Safety Evaluation
Palo Alto Networks
KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
Jun 3, 2025Yongjian Li, HaoCheng Chu, Yukun Yan +7Retrieval-Augmented Generation LLM Alignment
School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University · 2Tsinghua Laboratory of Brain and Intelligence · School of Informatics, Xiamen University +6
C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Jun 2, 2025Ping Wu, Guobin Shen, Dongcheng Zhao +6Value Alignment LLM Alignment
BrainCog Lab, Institute of Automation, Chinese Academy of Sciences, Beijing, China · The School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Beijing Key Laboratory of Safe AI and Superalignment, Beijing, China +2
Doubly Robust Alignment for Large Language Models
Jun 1, 2025Erhan Xu, Kai Ye, Hongyi Zhou +3LLM Alignment RL from Human Feedback
Department of Statistics, LSE, London, UK · Department of Mathematics, Tsinghua University, Beijing, China · School of Design, LCC, UAL, London, UK +1
Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective
May 30, 2025Erfan LoghmaniLLM Alignment LLM Fine-Tuning
Foster School of Business University of Washington Seattle, WA 98195
InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
May 20, 2025Yanggan Gu, Yuanyi Wang, Zhaoyi Yan +4Language Model Merging LLM Alignment
The Hong Kong Polytechnic University (PolyU) · Zhejiang University · PolyU-Daya Bay Technology and Innovation Research Institute
R3: Robust Rubric-Agnostic Reward Models
May 19, 2025David Anugraha, Zilu Tang, Lester James V. Miranda +5Reward Modeling LLM Evaluation
Department of Computer Science, Stanford University · Department of Computer Science, Boston University · Allen Institute for AI +4
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
May 19, 2025Kangwen Zhao, Jianfeng Cai, Jinhua Zhu +5Reward Modeling LLM Alignment
University of Science and Technology of China

Jan 8, 2026J/K move · Enter open · S save

Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes

Yonghyun Jun, Junhyuk Choi, Jeonghyun Park, Jihyeong Park+2

Chung-Ang University, Seoul, Korea

LLM Alignment Personality Modeling in Language Models LLM Agent Evaluation Conversational Agents

Open paper AskPDF arXiv

While Large Language Model (LLM) role-playing agents have advanced rapidly, it remains unclear which profile elements genuinely drive role-playing quality. To bridge this gap, we introduce a systematic diagnostic framework that disentangles the impact of character profiles along three axes: Familiarity (Known vs. Unknown), Structure (Structured vs. Unstructured), and Disposition (Moral vs. Immoral). Utilizing a unified hierarchical schema (5 dimensions, 28 fields), we construct a controlled dataset of 211 personas and evaluate five LLMs on both single- and multi-turn interactions. Our results reveal a striking asymmetry: Familiarity and Structure show negligible impact, while Disposition produces large, consistent performance degradation for immoral characters across all conditions. Further analyses suggest that the Moral--Immoral gap is amplified by post-SFT alignment, and that this degradation varies substantially across profile attributes. To mitigate this bottleneck, we propose Field-Aware Contrastive Decoding (FACD), a training-free strategy that amplifies suppressed disposition-sensitive signals, significantly closing the performance gap without sacrificing moral-character performance.