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

Multi-Adapter Representation Interventions via Energy Calibration
May 27, 2026Manjiang Yu, Hongji Li, Junwei Chen +4LLM Alignment LLM Safety Alignment
The University of Queensland, Brisbane, Australia · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · Institute of Science Tokyo, Tokyo, Japan
The Attentional White Bear Effect in Transformer Language Models
May 27, 2026Rebecca Ramnauth, Brian ScassellatiTransformer Interpretability LLM Alignment
Yale University New Haven, CT, USA
AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates
May 27, 2026Shaolong Chen, Madalina Ciobanu, Qingqing Mao +1LLM Alignment Direct Preference Optimization
Incept Labs Houston, TX · Incept Labs, Houston, TX · Titan Holdings, San Francisco, CA
Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
May 27, 2026Seojin Hwang, Minju Kim, Junhyuk Choi +2LLM Alignment Framing Effects in Language Models
Chung-Ang University, Seoul, Korea
Behavioural Analysis of Alignment Faking
May 26, 2026Nathaniel Mitrani Hadida, Rhea Karty, David Williams-King +1LLM Alignment Value Alignment
University of Cambridge · ERA · Harvard University +1
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
May 26, 2026Dongyoon Hahm, Dylan Hadfield-Menell, Kimin LeeLLM Alignment Data Poisoning Attacks
1KAIST · 2MIT
In LLM Reasoning, there is Irrationality on top of Value Misalignment
May 26, 2026Kejiang Qian, Fengxiang HeLLM Alignment LLM Reasoning
University of Edinburgh
Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations
May 26, 2026Mohammad Amine Jradi, Faeze Ghorbanpour, Alexander FraserLLM Evaluation LLM Alignment
School of Computation, Information and Technology, TU Munich Munich Center for Machine Learning (MCML)
Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
May 26, 2026Lulu Zheng, Wenjin Yang, Xiangwen Zhang +4LLM Alignment LLM-as-a-Judge
AMAP, Alibaba Group · Beihang University
KARMA: Karma-Aligned Reward Model Adaptation
May 26, 2026Jared Scott, Jesse RobertsReward Modeling RL for Language Models
Tennessee Tech University Cookeville, Tennessee
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
May 26, 2026Sil Hamilton, David MimnoLLM Alignment Diverse Text Generation
Department of Information Science Cornell University
Curriculum Learning for Safety Alignment
May 25, 2026Sandeep Kumar, Virginia Smith, Chhavi YadavLLM Alignment Direct Preference Optimization
Carnegie Mellon University · Simons Institute, UC Berkeley
CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations
May 25, 2026Mike Zhang, Ali Basirat, Desmond ElliottMultilingual Language Models LLM Alignment
Department of Computer Science (DIKU), University of Copenhagen · Centre for Language Technology (CST), University of Copenhagen · Pioneer Centre for Artificial Intelligence
Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning
May 25, 2026Bo Zou, Chao XuFine-Tuning LLM Alignment
MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
May 25, 2026Linhao Luo, Thuy-Trang Vu, Van-Anh Nguyen +3LLM Alignment Inference-Time Optimization
Monash University · Defence Science and Technology Group, Australia
Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts
May 24, 2026Niklas Weller, Emilio BarkettAI-Assisted Decision Making LLM Alignment
University of St. Gallen, Switzerland · 2Columbia University, New York, NY USA.
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
May 24, 2026Jingyi Sun, Qianli Wang, Pepa Atanasova +2CoT Faithfulness Contextual Faithfulness
University of Copenhagen · 2Technische Universität Berlin · 3German Research Center for Artificial Intelligence (DFKI) +2
Emotional intelligence in large language models is fragmented across perception, cognition, and interaction
May 23, 2026Minghao Lv, Lu Chen, Enchang Zhang +6LLM Evaluation LLM Alignment
X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China. · MoE Key Lab of Artificial Intelligence. · Jiangsu Key Lab of Language Computing, China. +1
Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol
May 23, 2026Yuki NakamuraLLM Alignment Mechanistic Interpretability
The Open University of Japan
Convex Optimization for Alignment and Preference Learning on a Single GPU
May 22, 2026Miria Feng, Mert PilanciPairwise Preference Learning LLM Alignment
Department of Electrical Engineering, Stanford University, California, United States.
Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts
May 21, 2026Andrii KryshtalLLM Alignment Language Model Safety Evaluation
BlueDot Impact Technical AI Safety Sprint · Independent Researcher
Token-weighted Direct Preference Optimization with Attention
May 21, 2026Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1Pairwise Preference Learning LLM Alignment
Cornell University · Vanderbilt University
Hypergraph as Language
May 21, 2026Mengqi Lei, Guohuan Xie, Shihui Ying +4LLM Alignment Hypergraph Learning
1{BNRist, THUIBCS, BLBCI, School of Software}, Tsinghua University · 2Yangtze Delta Region Institute, Tsinghua University · 3Shanghai Institute of Applied Mathematics and Mechanics, Shanghai University +1
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
May 20, 2026Hao Chen, Qi Zhang, Liyao Li +7LLM Alignment LLM Fine-Tuning
Zhejiang University · Ant Group · Eastern Institute of Technology
Towards Context-Invariant Safety Alignment for Large Language Models
May 20, 2026Yixu Wang, Yang Yao, Xin Wang +4RL for Language Models LLM Alignment
Fudan University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China.
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
May 20, 2026Zhiqin Yang, Yonggang Zhang, Wei Xue +3LLM Alignment Direct Preference Optimization
1The Hong Kong University of Science and Technology · 2LIGHTSPEED · 3Hong Kong Baptist University.
Refining and Reusing Annotation Guidelines for LLM Annotation
May 20, 2026Kon Woo Kim, Jin-Dong Kim, Akiko AizawaLLM Alignment LLM-Assisted Annotation
The Graduate University for Advanced Studies, SOKENDAI · National Institute of Informatics (NII) · BioData Science Initiative (BSI), National Institute of Genetics (NIG)
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
May 18, 2026Sangwoo Park, Woongyeong Yeo, Seanie Lee +6Contextual Integrity LLM Alignment
KAIST
Alignment Dynamics in LLM Fine-Tuning
May 18, 2026Yuhan Huang, Huanran Chen, Yinpeng DongLLM Alignment LLM Fine-Tuning
Shanghai Qi Zhi Institue & University of Tokyo · College of AI, Tsinghua University · Shanghai Qi Zhi Institue
Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation
May 18, 2026Guining Cao, Jiaxin Peng, Chu Zeng +3Pairwise Preference Learning Open-Ended Generation
Xingchen AGI Lab, China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd · School of Software and Microelectronics, Peking University · Tsinghua University

May 27, 2026, cs.AIJ/K move · Enter open · S save

Multi-Adapter Representation Interventions via Energy Calibration

Manjiang Yu, Hongji Li, Junwei Chen, Xue Li+3

The University of Queensland, Brisbane, Australia · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · Institute of Science Tokyo, Tokyo, Japan

LLM Alignment LLM Safety Alignment Causal Interventions in Language Models

Open paper AskPDF arXiv

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction and strength vary substantially across samples, and such indiscriminate intervention leads to degradation of general capabilities on benign inputs. To address these challenges, we propose Multi-Adapter Representation Interventions via Energy Calibration (MARI). Specifically, we introduce a competitive multi-adapter mechanism in which specialized experts capture non-linear correction patterns and adaptively determine the appropriate intervention direction and strength for different samples. Furthermore, we design an energy-based gating module that leverages internal propagation dynamics to distinguish inputs that are applicable for intervention. Extensive experiments across diverse model families and parameter scales demonstrate that MARI achieves state-of-the-art alignment performance. Our method significantly improves performance on TruthfulQA, BBQ, and safety benchmarks, while maintaining and even improving general capabilities on tasks such as MMLU and ARC. Our code is available at https://github.com/V1centNevwake/MARI.

Momentum

Related topics

Latest papers 422