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

Asymmetric Communication: Large Language Models and Language Games
Jul 30, 2026Enzo FenoglioLLM Alignment Human-AI Interaction
Dept. Computer Science University College London 66-72 Gower Street, London WC1E 6EA, UK
Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters
Jul 30, 2026Pankayaraj Pathmanathan, Furong HuangLLM Alignment LLM Safety Alignment
University of Maryland College Park
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment
Jul 29, 2026Seonglae Cho, Adriano KoshiyamaLLM Alignment Language Model Bias Evaluation
1Holistic AI · University College London
DIRECT: Direct Decoding for Efficient and Aligned Sequence Labeling with Large Language Models
Jul 29, 2026Yilei Wang, Jiaxin Gan, Kexuan Zhang +3LLM Alignment LLM Information Extraction
College of Computer and Data Science, Fuzhou University, Fuzhou, 350108, China · School of Computer Science, Peking University, Beijing, 100871, China
Constitutional Midtraining: Content Presence Drives Alignment Gains
Jul 29, 2026Desiree Cho, Cameron Tice, Bernie Hogan +4LLM Alignment LLM Safety Alignment
Department of Computer Science, University of Oxford · Institute for Ethics in AI, University of Oxford · 3Geodesic Research +1
Misalignment Has a Personality: A Big Five Account of Emergent Misalignment
Jul 29, 2026Hasibur Rahman, Smit DesaiLLM Alignment Personality Modeling in Language Models
Northeastern University Boston, MA, US
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
Jul 28, 2026Anton de la Fuente, Arthur ConmySupervised Fine-Tuning LLM Alignment
MemSFT: Mitigating Alignment Tax with an External Parametric Memory
Jul 28, 2026Jiarui Wang, Xiang Shi, Jiaqi Cao +8LLM Alignment Memory-Augmented Language Models
LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Shanghai AI Laboratory · School of Computer Science, Shanghai Jiao Tong University +1
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
Jul 28, 2026Yu Yan, Jiahao Chen, Siqi Lu +6LLM Alignment Adversarial Attacks on LLMs
College of Computer Science and Technology, Zhejiang University · Henan Key Laboratory of Network Cryptography Technology, Information Engineering University · State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences
Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback
Jul 28, 2026Yunpeng ChuLLM Alignment Reward Shaping
Stony Brook University
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Jul 27, 2026Md Rezwanul Haque, Md. Milon Islam, Fakhri KarrayRL for Language Models LLM Alignment
Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo, N2L 3G1, Ontario, Canada · Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, Bangladesh · Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Inverse RL Helps Align AI by Imitating Humans
Jul 27, 2026Michał Wiliński, Liu Leqi, Chirag NagpalRL for Language Models LLM Alignment
Carnegie Mellon University · The University of Texas at Austin · Independent Researcher
DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models
Jul 27, 2026Hao Yang, Jin Wang, Xuejie ZhangLLM Alignment Multimodal Large Language Models
School of Information Science and Engineering Yunnan University Kunming, China
Auditing Alignment Controllability in LLMs via Political Axes
Jul 26, 2026Bartol Bućan, Nikola Sočec, Sarah Isufi +5LLM Alignment Language Model Steering
Student at University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia · It From Bit d.o.o., Zagreb, Croatia · University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia
Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning
Jul 25, 2026Adhyyan Narang, Artin Tajdini, Claire Zhang +1LLM Alignment Emergent Misalignment in Language Models
University of Washington
Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining
Jul 25, 2026Rares A. C. Diaconescu, Iulia Slanina, Alina Florea +5LLM Alignment LLM Safety Alignment
Delft University of Technology
LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment
Jul 25, 2026Pascal Ekin, Hyosun Choi, Wei JieLLM Alignment Low-Rank Adaptation
Royal Holloway, University of London, United Kingdom · University of West London, United Kingdom
Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning
Jul 25, 2026Xiaokun Wang, Siyu Song, Wentao Liu +1LLM Alignment Intelligent Tutoring Systems
East China Normal University, Shanghai, China · Shanghai Chuangjie Situo Information Technology Co., Ltd., Shanghai, China · Shanghai Normal University, Shanghai, China +1
A Roadmap to Impactful Pluralistic Alignment Research
Jul 24, 2026Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh +3LLM Alignment Pluralistic Alignment
1Massachusetts Institute of Technology · University of Washington · 3Carnegie Mellon University
A Unified Moral-Value Dataset for Instruction Tuning
Jul 23, 2026Zhaohui Zeng, Florian MaiLLM Alignment Moral Reasoning in Language Models
1RWTH Aachen · University of Bonn · 3Lamarr Institute for Machine Learning and Artificial Intelligence
LKValues: Aligning Large Language Models with Sri Lankan Societal Values
Jul 22, 2026Nethmi Muthugala, Supryadi, Surangika Ranathunga +7Multilingual Language Model Evaluation LLM Alignment
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
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
Jul 22, 2026Haran Shani-Narkiss, Michael Fire, Oren TsurLLM Evaluation LLM Alignment
University College London, London, England. · Ben-Gurion University of the Negev, Be’er Sheba, Israel.
D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios
Jul 22, 2026Siyi Hao, Yidi Cao, Linhao Yu +2LLM Evaluation LLM Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · The International Joint Institute of Tianjin University, Fuzhou, China
Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs
Jul 21, 2026Alexander ManevMultilingual Language Model Evaluation LLM Alignment
Technical University of Munich
Measuring Reward-Seeking via Contrastive Belief Updates
Jul 21, 2026Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya +5RL for Language Models LLM Alignment
Apollo Research · OpenAI
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
Jul 21, 2026Seunghyun Lee, Dongyoon Han, Sangdoo YunLLM Alignment LLM Refusal
NAVER AI Lab
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
Jul 20, 2026Prakhar Gupta, Terry Jingchen Zhang, Florent Draye +2LLM Sycophancy LLM Alignment
University of Michigan · Jinesis Lab, University of Toronto & Vector Institute · Max-Planck Institute for Intelligent Systems, Tübingen, Germany +2
Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila
Jul 20, 2026Supryadi, Irfan, Julianti +4LLM Evaluation LLM Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · Universitas Universal, Indonesia · Beijing Language and Culture University, Beijing, China +2
A Geometric Perspective on Stabilizing Value Conflict Resolution
Jul 20, 2026Saket Reddy, Andy LiuLLM Alignment Moral Reasoning in Language Models
Supervised Program for Alignment Research (SPAR) · University of Illinois - Urbana-Champaign · Carnegie Mellon University
Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment
Jul 19, 2026Wentao Liu, Siyu Song, Xi Chen +4LLM Alignment Large Language Model-Based Role-Play Simulation
1Shanghai Institute of Innovation · 2East China Normal University · University of Science and Technology of China +3

Jul 30, 2026, cs.CYJ/K move · Enter open · S save

Asymmetric Communication: Large Language Models and Language Games

Enzo Fenoglio

Dept. Computer Science University College London 66-72 Gower Street, London WC1E 6EA, UK

LLM Alignment Human-AI Interaction AI Agent Governance

Open paper AskPDF arXiv

Contemporary AI discourse attributes to language models properties they cannot bear: general intelligence as substrate-independent cognition, hallucination as cognitive failure, agency as autonomous goal-pursuit, sentience as emergent inner life, alignment as goal synchronization. This paper argues that these are instances of a single category mistake--properties constituted within human communicative practice are projected onto the machine side--and explains its structure. Human-LLM interaction constitutes a language game in which one side bears all normative activity. We call this configuration asymmetric communication since model outputs circulate communicatively, entering further exchanges, without the system undertaking commitments, bearing entitlements, or performing the assessment on which discursive standing depends. Three conditions define the asymmetry: (i) correctness is enforced exclusively by the receiver; (ii) accountability is borne by human participants alone; and (iii) the practical standing of any output depends entirely on human uptake. These conditions are structural, hold independently of capability, and remain unchanged as more powerful models raise the stakes of misattribution. The framework draws on Wittgenstein (meaning enacted in shared practices), Luhmann (communication completed on the receiver's side), Esposito (algorithmic contingency sufficient for uptake), and Brandom (normative scorekeeping as the source of discursive standing). Applied to all five, it reclassifies each as a receiver-side phenomenon, grounds guardrails as structural necessities rather than manifestations of machine moral agency, and yields an implication for AI governance. Alignment is institutional constraint engineering, not goal synchronization between agents, while responsibility remains with human institutions.

Momentum

Related topics

Latest papers 422